Publications

Research Areas

[RL]=Reinforcement Learning [IA]=Intelligent Autonomy

[SC]=Stochastic Control [TS]=Transportation Systems

[GT]=Game Theory [PS]=Power Systems

[QT]=Queueing Theory [CN]=Communication Networks

Preprints

• [RL] R. Agrawal, N. Dahlin, R. Jain and A. Nayyar, ``Conditional Kernel Imitation Learning for Continuous State Environments", 2023: arxiv:2308:12573. (submitted)

• [RL] K.C. Kalagarla*, R. Jain, and P. Nuzzo, “A Safe Bayesian Learning Algorithm for Constrained MDPs with Bounded Constraint Violation”, 2023. arxiv:2301.11547. (submitted)

• [RL] D. Tang, Rahul Jain, A. Nayyar and P. Nuzzo, “Posterior Sampling-based Online Learning for Episodic POMDPs”,  (arXiv:2310.10107). (submitted)

• [RL] D. Tang, B. Hao, Rahul Jain, and Z. Wen, “Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach”, (arXiv:2310.11531). (submitted)

Unpublished Manuscripts

AI/ML Conference Papers

• • [RL] A. Agnihotri*, R. Jain, and H. Luo, “ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints”, arxiv: 2302.00808, 2023. (submitted), accepted: ICML 2024.

  • [RL] Mehdi Jafarnia*, Rahul Jain and Ashutosh Nayyar, “A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitratry Opponent”, AISTATS 2024. (arxiv:2109.03396)

  • [RL] K.C. Kalagarla*, Rahul Jain, and P. Nuzzo, “Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation”, NeurIPS Workshop on Optimization in ML, 2023.

  • [RL] A. Agnihotri*, Rahul Jain, and H. Luo, “Average-reward Constrained Policy Optimization”, NeurIPS Workshop on Optimization in ML, 2023.

  • [RL] B. Hao, Rahul Jain, D. Tang, B. Van Roy and Z. Wen, “Bridging imitation and online reinforcement: An optimistic tale”, Trans. on Machine Learning Research (TMLR), September 2023. (arXiv:2303.11369)

  • [RL] Mehdi Jafarnia*, LiyuChen*, Rahul Jain and Haipeng Luo,“Posterior Sampling-based Online Learning for the Stochastic Shortest Path Model”, Proc. UAI 2023. (arXiv:2106.05335). 

  • [RL] B. Hao, Rahul Jain, T. Lattimore, B. Van Roy and Z. Wen, “Leveraging demonstrations to improve online learning: Quality matters”, Proc. ICML 2023. (arxiv:2302.03319)

  • [RL] D. Kartik*, K.C. Kalagarla*, R. Jain, A. Nayyar and P. Nuzzo, “Optimal Control of Partially Observable Markov Decision Processes with Finite Linear Temporal Logic Constraints", Proc. UAI, 2022. (arXiv:2203.09038)

  • [RL] Liyu Chen*, Rahul Jain and Haipeng Luo, “Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP”, Proc. ICML 2022. (arXiv:2112.09859)

  • [RL] Liyu Chen*,RahulJain and Haipeng Luo,“Learning Infinite-Horizon  Average-Reward Markov Decision Processes with Constraints”, Proc. ICML 2022. (arXiv:2202.00150). 

  • [RL] Mehdi Jafarnia*, Rahul Jain and Ashutosh Nayyar, “Online Learning for Partially Observable MDPs”, AISTATS 2022. (arxiv:2102.12661)

  • [RL] Liyu Chen*, Mehdi Jafarnia*, Rahul Jain and Haipeng Luo, “Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path”, Proc. NeurIPS, 2021. (arXiv:2106.08377)

  • [RL] Krishna C. Kalagarla*, Rahul Jain and Pierluigi Nuzzo, “A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints”, Proc. AAAI Conf. on AI, 2021. (arXiv:2009.11348)

  • [RL] Chen-Yu Wei, Mehdi Jafarnia*, Haipeng Luo, Hiteshi Sharma*,and Rahul Jain, “Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation”, Proc. AISTATS, 2021. (arXiv:2007.11849)

  • [RL] Mehdi Jafarnia*, Liyu Chen*, Rahul Jain and Haipeng Luo, ‘Online Learning for Stochastic Shortest Path Model via Posterior Sampling”, ICML Workshop on Reinforcement Learning, July 2021. (arXiv:2106.05335)

  • [RL] Liyu Chen*, Mehdi Jafarnia*, Rahul Jain and Haipeng Luo, “Implicit Finite-Horizon Ap- proximation and Efficient Optimal Algorithms for Stochastic Shortest Path”, ICML Workshop on Reinforcement Learning, July 2021. (arXiv:2106.08377)

  • [IA] Nathan Dahlin*, Krishna C. Kalagarla*, Nikhil Naik, Rahul Jain and Pierluigi Nuzzo, “Designing Interpretable Approximations to Deep Reinforcement Learning”, ICML Workshop on Reinforcement Learning, 2021. (arXiv:2010.14785)

  • [RL] Chen-Yu Wei, Mehdi Jafarnia*, Haipeng Luo, Hiteshi Sharma* and Rahul Jain, “ Model- free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes”, Proc. ICML (International Conf. on Machine Learning), July 2020.  (arXiv:2007.11849)

  • [RL] Hiteshi Sharma*, Mehdi Jafarnia*, and Rahul Jain, “Approximate Relative Value Learning for Continuous MDPs”, Proc. Conference on Uncertainty in Artificial Intelligence (UAI), July 2019. (acceptance rate: 26%) 

  • [RL] Yi Ouyang*, Mukul Gagrani*, Ashutosh Nayyar and Rahul Jain, “Learning Unknown Markov Decision Processes: A Thompson Sampling Approach”, Proc. Adv. Neural Information Proc. Symp. (NIPS), 2017. (arXiv:1709.04570 )
    
    

Journal Publications

• [RL] B. Hao, Rahul Jain, D. Tang, B. Van Roy and Z. Wen, “Bridging imitation and online reinforcement: An optimistic tale”, Trans. on Machine Learning Research (TMLR), September 2023. (arXiv:2303.11369)

• [RL] Abhishek Gupta*, Rahul Jain and Peter Glynn,“Probabilistic Contraction Analysis of Iterated Random Operators”, IEEE T. Automatic Control, accepted: September 2023. (arXiv:1804.01195)

• [SC] Sagar Sudhakar*, Dhruva Kartik*, Ashutosh Nayyar and Rahul Jain, “Optimal communication and control strategies in a multi-agent MDP problem”, IEEE T. on Automatic Control, accepted: October 2023.

• [PS] Nathan Dahlin*, Rahul Jain, “Scheduling flexible non-premptive loads in smart-grid networks”, IEEE T. Control of Networked Systems (TCNS), 9(1):14-24, 2022. (arXiv:2003.13220)

• [PS] Nathan Dahlin*, Rahul Jain, “Two-Stage Electricity Markets with Renewable Energy Integration: Market Mechanisms and Equilibrium Analysis”, IEEE T. Control of Networked Systems (TCNS), 9(2):823-834, 2022. (arXiv:1909.00508)

• [QT] Mehdi Jafarnia* and Rahul Jain, “Non-indexability of the Stochastic Appointment Scheduling Problem”, Automatica, Vol. 118, August 2020. (arXiv:1708.06398)

• [RL] Yi Ouyang*, Mukul Gagrani*, and Rahul Jain, “Posterior Sampling-based Reinforcement Learning for Control of Unknown Linear Systems”, IEEE Trans. Automatic Control, 65(8):3600-3607, 2020. (arXiv:1709.04047)

• [RL][SC] William Haskell, Pengqian Yu, Hiteshi Sharma* and Rahul Jain, “A Universal Empirical dynamic programming algorithm for Continuous State Space MDPs”, IEEE Trans. Automatic Control, 65(1):115-129, 2020. (arXiv:1709.07506)

• [RL] Dileep Kalathil, Vivek Borkar and Rahul Jain, “Empirical Q-Value Iteration”, Stochastic Systems, Oct., 2020. (arXiv:1412.0180)

• [PS] Wenyuan Tang and Rahul Jain,  “Aggregating Correlated Wind Power with Full Surplus Extraction”, IEEE Trans. on Smart-grid, 9(6):6030-6038, Nov. 2018.

• [RL] Naumaan Nayyar, Dileep Kalathil and Rahul Jain, “On regret-optimal learning in decentralized multi-armed bandits”, IEEE Trans. on Control of Networked Systems, 5(1):597-606, 2018. (arXiv:1505.00553)

• [SC] Naumaan Nayyar, Dileep Kalathil and Rahul Jain, “Optimal decentralized control for asymmetric delayed information sharing”, IEEE Trans. Control of Networked Systems, 5(1):653-663, 2018.

• [SC] Dileep Kalathil, Vivek Borkar and Rahul Jain, “Approachability in Stackelberg Stochastic games with Vector Costs”, Dynamic Games & Applications, 7(3):422-442, 2017. (arXiv:1411.0728)

• [PS] Wenyuan Tang and Rahul Jain, “Dynamic economic dispatch: The Value of storage”, IEEE T. on Smart-Grid, 7(5):2350-2358, 2016. 

• [RL][SC] William Haskell, Rahul Jain and Dileep Kalathil, “Empirical Dynamic Programming”, Math. of Operations Research, 41(2): 402-429, 2016.  (on arxiv) 

• [PS] Wenyuan Tang and Rahul Jain, “Market mechanisms for buying random wind”, IEEE Trans. on Sustainable Energy, 6(4):1615-1623, 2015. (on arxiv) 

• [SC] William Haskell and Rahul Jain, “A Convex Analytic Approach to Risk-aware Markov Decision Processes”, SIAM J. of Control and Optimization, 53(3): 1569-1598, 2015. 

• [QT] Harsha Honnappa, Rahul Jain and A. Ward, A queueing model with independent arrivals, and its’ fluid and diffusion limits”, Queueing Systems, 80(1-2): 71-103, 2015. (on arxiv) 

• [QT] Harsha Honnappa and Rahul Jain, “Strategic arrivals into queueing networks: The network concert queueing game”, Operations Research, 63(1):247 - 259, 2015. (on arxiv)

• [RL][SC] Vivek Borkar and Rahul Jain, “Risk-constrained Markov decision processes”, IEEE Trans. on Automatic Control, 59(9):2574-2579, 2014.

• [RL] Dileep Kalathil, Naumaan Nayyar and Rahul Jain, “Decentralized learning for multi-player multi-armed bandits”, IEEE Trans. on Information Theory, 60(4):2331-2345, April 2014. (on arxiv)

• [QT] Parijat Dube and Rahul Jain, “Bertrand equilibria and efficiency in markets for congestible network services”, Automatica, 50(3):756-767, 2014

• [CN] Srinivas Yerramalli, Rahul Jain and Urbashi Mitra, “Coalitional games for transmitter cooperation in wireless networks”, IEEE Trans. on Signal Processing, 62(4):757-771, 2014. (on arxiv) 

• [SC] William Haskell and Rahul Jain, “Stochastic dominance-constrained Markov decision processes”, SIAM J. of Control and Optimization, 51(1):273-303, 2013. (on arxiv)

• [CN] Dileep Kalathil and Rahul Jain, “Spectrum sharing through contracts for cognitive radios”, IEEE T. Mobile Computing, 12(10):1999-2011, October 2013. 

• [CN][GT] Wenyuan Tang and Rahul Jain, “Hierarchical auction mechanisms for network resource allocation”, IEEE J. Selected Areas in Comm., 30(11):2117-2125, Nov. 2012.  

• [CN][GT] Rahul Jain, “Network market design I: Bandwidth markets”, (invited paper) IEEE Communications Magazine special issue on Communication networks economics, 50(11):78-83, 2012.

• [SC] Yi Gai, Bhaskar Krishnamachari and Rahul Jain, “Combinatorial network optimization with unknown variables: Multi-armed bandits with linear rewards and individual observations”, IEEE/ACM Trans. on Networking, 20(5):1466-1478, 2012.

• [GT] Rahul Jain, Sandeep Juneja and Nahum Shimkin, “The concert queueing game: To wait or to be late”, Discrete Event Dynamic Systems, 21(1):103-134, 2011.

• [SC] Rahul Jain and Pravin Varaiya, “Simulation-based optimization of Markov decision processes: An empirical process theory approach”, Automatica, 46(8):1297-1304, August 2010.

• [CN] Rahul Jain and Jean Walrand, “An efficient Nash-implementation mechanism for divisible resource allocation”,  Automatica, 46(8):1276-1283, August 2010.

• [CN] Charis Kaskiris, Rahul Jain, Ram Rajagopal and Pravin Varaiya, “Combinatorial Auction Bandwidth Trading: An Experimental Study”, in Developments in Experimental Economics, Springer Lecture Notes in Economics and Mathematical Systems, 2007.

• [SC] Rahul Jain and Pravin Varaiya, “Simulation-based uniform value function estimates of Markov decision processes”, SIAM J. Control and Optimization, 45(5):1633-1656, November 2006.

• [GT] Rahul Jain and Pravin Varaiya, “Combinatorial exchange mechanisms for efficient bandwidth allocation”, Communications in Information and Systems, 3(4):305-324, September 2004.

• [SC] Tunc Simsek, Rahul Jain and P.Pravin Varaiya, “Scalar estimation and control with noisy binary observations”, IEEE Trans. Automatic Control, 49(9):1598-1603, September 2004.

• [CN] Rahul Jain, Anuj Puri and Raja Sengupta, “Geographical routing for wireless ad hoc networks using partial information”, IEEE Personal Communications, 8(1):48-57, February 2001.

• Rahul Jain, “Key distribution and authentication protocol for secure wireless conferencing”, IETE Technical Review, 15(6):471-476, December 1998.

Other Conference Papers

• • [RL] Krishna C. Kalagarla*, Matthew Low*, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo, “Scalable Assume-Guarantee Optimal Planning for Logically Constrained Multi-Agent Markov Decision Processes”, submitted: Proc. IEEE CDC 2024.

  • [RL] Kevin Chang*, Nathan Dahlin, Rahul Jain, and Pierluigi Nuzzo, “Exact and Cost-Effective Automated Transformation of Neural Network Controllers to Decision Tree Controllers”, Proc. IEEE CDC 2023.

  • [SC] Dengwang Tang*, Ashutosh Nayyar and Rahul Jain, “A Novel Point-based Algorithm for Multi-agent Control Using the Common Information approach”, Proc. IEEE CDC 2023. (arxiv:2304.04346)

  • [RL] William Chang, Mehdi Jafarnia*, and Rahul Jain, “Online Learning for Cooperative Multi-Player Multi-Armed Bandits”, Proc. IEEE CDC 2022. (arxiv:2109.03818).

  • [RL] Nathan Dahlin*, Kevin C. Chang*, Krishna C. Kalagarla*, Rahul Jain and Pierluigi Nuzzo, “Practical Control Design for the Deep Learning Age: Distillation of Deep RL-Based Controllers”, Proc. Allerton Conf. 2022. (arXiv:2010.14785)

  • [RL] William Chang*, Mehdi Jafarnia*, and Rahul Jain, “Online Learning for Cooperative Multi-Player Multi-Armed Bandits”, IEEE CDC 2022. (arxiv:2109.03818)

  • [SC] Dhruva Kartik*, Sagar Sudhakara*, Rahul Jain, Ashutosh Nayyar, ``Optimal Communication and Control Strategies for a Multi-Agent System in the Presence of an Adversary",  Proc. IEEE CDC 2022. 

  • [IA] Krishna C. Kalagarla*, Rahul Jain and Pierluigi Nuzzo, “Cost Optimal Control of Markov Decision Processes Under Signal Temporal Logic Constraints”, to appear Proc. Indian Control Conf. (ICC), Dec. 2021.

  • [IA] Krishna C. Kalagarla*, Rahul Jain and Pierluigi Nuzzo, “Model-Free Reinforcement Learning for Optimal Control of Markov Decision Processes Under Signal Temporal Logic Specifications”, Proc. IEEE Control and Decision Conf. (CDC), Dec. 2021. (arXiv:2109.13377).

  • [IA] Krishna C. Kalagarla*, Rahul Jain and Pierluigi Nuzzo, “Optimal Control of Discounted- Reward Markov Decision Processes Under Linear Temporal Logic Specifications”, Proc. American Control Conf. (ACC), July 2021. (arXiv:2011.00632)

  • [RL] Hiteshi Sharma*, and Rahul Jain, “Finite Time Guarantees for Continuous State MDPs with Generative Model”, Proc. IEEE Control and Decision Conf. (CDC), March 2020. 

  • [PS] Nathan Dahlin* and Rahul Jain, “Scheduling of Flexible Non-Preemptive Loads”, Proc. IEEE Control and Decision Conf. (CDC), March 2020. (arXiv:2003.13220)

  • [PS] Nathan Dahlin*, Rahul Jain, “A Risk Aware Two-Stage Market Mechanism for Electricity with Renewable Generation”, Proc. American Control Conf. (ACC), 2020. (arXiv:2003.06119)

  • [RL] Hiteshi Sharma*, Rahul Jain and William Haskell,“Empirical algorithms for general stochastic systems with continuous states and actions”, Proc. IEEE Control and Decision Conf. (CDC), December 2019. 

  • [PS] Nathan Dahlin* and Rahul Jain, “A Two-Stage Market Mechanism for Electricity with Renewable Generation”, Proc. IEEE Control and Decision Conf. (CDC), December 2019. (arXiv:1909.00508)

  • [RL] Hiteshi Sharma* and Rahul Jain, “An Approximately Optimal Relative Value Learning Algorithm for Averaged MDPs with Continuous States and Actions”, Proc. Allerton Conf., September 2019. 

  • [RL] Hiteshi Sharma*, Rahul Jain, and Abhishek Gupta, “An Empirical Relative Value Learning Algorithm for Non-parametric MDPs with Continuous State Space”, Proc. European Control Conf. (ECC), 2019. 

  • [PS] Nathan Dahlin* and RahulJain,“A Two-Stage Mechanism for Selling Random Power”, Proc. American Control Conf. (ACC), 2019. (arXiv:1809.09873) 

  • [PS] Abhishek Gupta, B. Dakhil and Rahul Jain,“Dynamic Economic Dispatch and Price Evolution under Ramping Constraints and Uncertain Demand”, Proc. Allerton Conf., 2018. 

  • [SC] William Haskell and Rahul Jain, “A Random Monotone Operator Framework for Strongly Convex Stochastic Optimization”, Proc. IEEE Conf. on Decision and Control (CDC), 2017. 

  • [RL] William Haskell, Pengqian Yu, Hiteshi Sharma*, and Rahul Jain, “Randomized Function Fitting-based Empirical Value Iteration”, Proc. IEEE Conf. on Decision and Control (CDC), 2017. 

  • [SC] William Haskell and Rahul Jain, “Inexact iteration of averaged operators for non-strongly convex stochastic optimization”, Proc. Allerton Conf., 2017. 

  • [RL] Yi Ouyang*, Mukul Gagrani*, and Rahul Jain, “Control of Unknown Linear Systems with Thompson Sampling”, Proc. Allerton Conf., 2017. (arXiv:1709.04047 )

  • [TS] Yi Ouyang*, Rahul Jain and Pravin Varaiya, “On the existence of fixed time control of traffic intersection signals”, Proc. Allerton Conference, 2016. (Invited) 

  • [SC] William Haskell, Rahul Jain and Hiteshi Sharma*, “A Dynamical Systems Framework for Stochastic Iterative Optimization”, Proc. IEEE Conf. on Decision and Control (CDC), 2016. (Invited) 

  • [PS] Wenyuan Tang*, Junjie Qin, Rahul Jain and Ram Rajagopal, “Pricing Sequential Forward Power Contracts”, Proc. IEEE International Conference on Smart Grid Communications (SmartGrid- Comm), Nov. 2015. 

  • [PS] Abhishek Gupta*, Rahul Jain, Kameshwar Poolla and Pravin Pravin Varaiya, “Equilibria in Two-Stage Electricity Markets”, Proc. IEEE Conf. on Decision and Control (CDC), Dec. 2015. 

  • [RL] Abhishek Gupta*, Rahul Jain and Peter Glynn, “An Empirical Algorithm for Relative Value Iteration for Average-cost MDPs”, Proc. IEEE Conf. on Decision and Control (CDC), Dec. 2015. 

  • [PS] Abhishek Gupta*, Rahul Jain and Ram Rajagopal, “Scheduling, pricing and efficiency of non- preemptive flexible loads under direct load control”, Proc. Allerton Conference, 2015. 

  • [QT] Harsha Honnappa*, Rahul Jain and Amy Ward, “Mean field limits by population acceleration”, Proc. IEEE Conf. on Decision and Control (CDC), Dec. 2014.

  • [PS] Wenyuan Tang*, Rahul Jain and Ram Rajagopal, “Stochastic dynamic pricing: Utilizing demand response in an adaptive manner”, Proc. IEEE CDC, Dec. 2014.

  • [RL] WilliamHaskell*,Dileep Kalathil* and Rahul Jain,“Empirical policy iteration for approximate dynamic programming”, Proc. IEEE CDC, Dec. 2014.

  • [RL] Dileep Kalathil*, Vivek Borkar and Rahul Jain, “Blackwell’s approachability in Stackelberg stochastic games: A learning version”, Proc. IEEE CDC, Dec. 2014.

  • [PS] Wenyuan Tang* and Rahul Jain, “Buying random yet correlated wind power”, Proc. IEEE International Conference on Smart Grid Communications (SmartGridComm), Nov. 2014.

  • [PS] Wenyuan Tang* and Rahul Jain, “Dynamic economic dispatch among strategic generators with storage systems”, Proc. Allerton Conference, Oct 2014.

  • [RL] WilliamHaskell*, Rahul Jain and Dileep Kalathil*,“Empirical value iteration for approximate dynamic programming”, Proc. American Control Conf., 2014. 

  • [SC] Naumaan Nayyar*, Dileep Kalathil* and Rahul Jain, “Optimal decentralized control in unidirectional one-step delayed sharing pattern with partial output feedback”, Proc. American Control Conf. (ACC), 2014. 

  • [HA] S. Kotova, Varun Sah*, Naumaan Nayyar* and Rahul Jain, “Thoracic epidural analgesia does not require prolonged urinary catheterization, Proc. Academic Surgical Congress 2014, San Diego, February 2014. 

  • [GT] Srinivas Yerramalli*, Rahul Jain and Urbashi Mitra, “Coalition formation for uplink device to device coordination with cooperation costs”, Proc. Asilomar Conference, 2013.

  • [PS] Wenyuan Tang* and Rahul Jain, “Game-theoretic analysis of the nodal pricing mechanism for electricity markets”, Proc. IEEE CDC 2013, March 2013.

  • [SC] Naumaan Nayyar*, Dileep Kalathil* and Rahul Jain, “Optimal decentralized control for unidirectional on-step delayed sharing pattern”, Proc. of The Allerton Conf., 2013. 

  • [RL] Dileep Kalathil*, Naumaan Nayyar* and Rahul Jain, “Decentralized learning for multi-player multi-armed bandits”, Proc. IEEE Conf. on Decision and Control (CDC), Dec 2012. 

  • [SC] William Haskell* and Rahul Jain, “Dominance-constrained Markov decision processes”, Proc. IEEE Conf. on Decision and Control (CDC), Dec 2012. 

  • [PS] Q. Wang, Mingyan Liu and Rahul Jain, “Dynamic pricing of power in smart-grid networks”, Proc. IEEE Conf. on Decision and Controls (CDC), Dec 2012. 

  • [QT] Harsha Honnappa*, Rahul Jain and Amy Ward, “A new transitory queueing model, and its’ process limits”, Proc. The ValueTools Conference, Oct. 2012. 

  • [RL] Dileep Kalathil*, Naumaan Nayyar* and Rahul Jain, “Multi-player multi-armed bandits: Decentralized learning with IID rewards”, Proc. The Allerton Conference, Oct. 2012. 

  • [QT] Harsha Honnappa*, Rahul Jain and Amy Ward, “The ∆(i)/GI/1 model: A new model of transitory queueing”, Proc. The Allerton Conference, Oct. 2012. 

  • [GT] Srinivas Yerramalli*, Rahul Jain and Urbashi Mitra, “Characterization of equilibria for the degraded Gaussian broadcast and sum power MAC channels””, Proc. The Allerton Conference, Oct. 2012. 

  • [GT] Srinivas Yerramalli*, Rahul Jain and Urbashi Mitra, “Stability of transmitter cooperation over a multiple access channel”, Proc. Intl. Conf. Sig. Proc. Comm. (SPCOM), August 2012. (Best student paper award) 

  • [GT] Srinivas Yerramalli*, Rahul Jain and Urbashi Mitra,“A game theoretic model for the Gaussian broadcast channel”, Proc. International Symposium on Information Theory (ISIT), June 2012. 

  • [GT] Dileep Kalathil* and Rahul Jain,“Incentives for cooperative relaying in a simple information-theoretic model, Proc. International Symp. on Information Theory (ISIT), June 2012. 

  • [PS] Wenyuan Tang* and Rahul Jain, “Stochastic resource auctions for renewable energy integration”, Proc. of The Allerton Conference on Systems, Communications and Control, Sep. 2011. 

  • [GT] Wenyuan Tang* and Rahul Jain, “Hierarchical auctions for network resource allocation”, Proc. of the International Conf. on Game Theory in Networks (GameNets), April 2011. 

  • [GT] Srinivas Yerramalli*, Rahul Jain and Urbashi Mitra, “Coalition games for transmitter co- operation in wireless networks”, Proc. International Symp. on Information Theory (ISIT), July 2011. 

  • [GT] Dileep Kalathil* and Rahul Jain, “Communication games on the generalized Gaussian relay channel”, Proc. of The Allerton Conf. on Systems, Communications and Control, Sep. 2010. 

  • [GT] Dileep Kalathil* and Rahul Jain, “A contracts-based approach to spectrum sharing in cognitive radio networks”, Proc. IEEE WiOpt (Intl. Symp. on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks) Conference, June 2010. 

  • [GT] Dileep Kalathil* and Rahul Jain, “Spectrum sharing through contracts”, Proc. of the IEEE DySpan Conference, April 2010. 

  • [SC] Vivek Borkar and Rahul Jain, “Risk-constrained Markov decision processes”, Proc. IEEE Control and Decision Conf. (CDC), December 2010. 

  • [RL] Yi Gai, Bhaskar Krishnamachari, and Rahul Jain, “Learning multi-user channel allocations in cognitive radio networks: A combinatorial multi-armed bandit formulation”, Proc. of the IEEE DySpan Conference, April 2010. 

  • [QT] Harsha Honnappa* and Rahul Jain, “Strategic arrivals into queueing networks”, Proc. of The Allerton Conference on Systems, Communications and Control, September 2010. 

  • [QT] Rahul Jain, Sandeep Juneja and Nahum Shimkin, “Queueing for timely service: Equilibrium analysis and social efficiency”, Proc. INFORMS MSOM (Manufacturing and Service Operations Management) Conference, Sep. 2010. 

  • [QT] Parijat Dube and Rahul Jain, “DiffServ pricing games in multi-class queueing network mod- els”, Proc. International Tele-traffic Conference (ITC), Sep. 2010. 

  • [QT] Parijat Dube and Rahul Jain, “Bertrand games between multi-class queues”, Proc. of the IEEE Control and Decision Conference (CDC), December 2009. 

  • [QT] Rahul Jain and Sandeep Juneja, “The concert/cafetaria queueing problem: A game of arrivals”, Proc. of the International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS Conference), October 2009. (Best paper award) 

  • [QT] Rahul Jain and Parijat Dube, “Queueing game models for differentiated services”, Proc. of the Int. Conf. on Game Theory in Networks (GameNets), May 2009. 

  • [QT] Parijat Dube and Rahul Jain, “N-player Bertrand and Cournot queueing games: Existence of equilibrium”, Proc. of The Allerton Conference on Systems, Communications and Control, September 2008. 

  • [GT] Rahul Jain and J. Walrand, “An efficient Nash-implementation mechanism for divisible resource allocation”, Proc. IEEE NOMS Workshop on Bandwidth on Demand, April 2008. 

  • [GT] Rahul Jain, “Designing a bipartite matching market”, Proc. of the IEEE Conf. on Decision and Control (CDC), December 2007. 

  • [RL] Rahul Jain and Pravin Varaiya, “PAC bounds for simulation-based optimization of Markov decision processes”, Proc. of the IEEE Control and Decision Conf. (CDC), Dec. 2007. (invited SIAM paper) 

  • [GT] A.Dimakis, Rahul Jain and J.Walrand, “Mechanisms for efficient allocation in divisible capacity networks”, Proc. of the IEEE Conf. Decision and Control (CDC), December 2006.

  • [GT] C. Kaskiris, Y. Butun and Rahul Jain, “An experimental analysis of a combinatorial market mechanism for bandwidth trading”, Proc. of the Workshop on Bandwidth Trading, Nov. 2006. 

  • [GT] Rahul Jain and Pravin Varaiya, “Efficient market mechanisms for network resource allocation”, Proc. of the IEEE Conf. Decision and Control (CDC), December 2005. (invited paper)

  • [GT] Rahul Jain, C. Kaskiris, Ram Rajagopal and Pravin Varaiya, “Combinatorial auction design for bandwidth trading: An experimental study”, Proc.  International Conf. on Experiments in Economic Sciences (EES), December 2004. 

  • [GT] Rahul Jain and Pravin Varaiya, “An efficient incentive-compatible combinatorial market mechanism”, Proc. of the Allerton Conf. on Systems, Communications and Control, Oct. 2004. 

  • [RL] Rahul Jain and Pravin Varaiya, “Simulation-based uniform value estimates of discounted and average reward MDPs”, Proc. IEEE Conf. Decision and Control (CDC), December 2004. 

  • [RL] Rahul Jain and Pravin Varaiya, “PAC learning for Markov decision processes and dynamic games”, Proc. IEEE Symp. on Information Theory (ISIT), June 2004. 

  • [RL] Rahul Jain and Pravin Varaiya,“Extensions to PAC learning for partially observable Markov decision processes”, Proc. Conf. Information Systems and Sciences (CISS), March 2004. 

  • [GT] Rahul Jain, Antonis Dimakis and Pravin Varaiya, “On the existence of competitive equilibria in bandwidth markets”, Proc. of the Allerton Conference on Systems, Communications and Control, October 2002. 

  • [SC] Tunc Simsek, Rahul Jain and Pravin Varaiya, “Control under communication constraints”, Proc. IEEE Conf. Decision and Control (CDC), December 2002. 

  • [CN] Mustafa Ergen, Sinem Coleri, B. Dundar, Rahul Jain, Anuj Puri, Pravin Varaiya,“Application of GPS to mobile IP and routing in wireless networks”, Proc. IEEE Vehicular Tech. Conf. (VTC), Sep. 2002. 

  • [CN] Rahul Jain, B. Sadeghi and E.W. Knightly, “Towards coarse-grained mobile-QoS”, Proc. IEEE WOWMOM (A Mobicom Workshop), August 1999. 

  • [CN] Rahul Jain and E.W. Knightly, “A framework for design and evaluation of mobile admission control algorithms”, Proc. IEEE Int. Conf. on Computer Comm. (INFOCOM), March 1999. 

  • [RL] Rahul Jain, G.Rajaram, S.Gupta, S.Subramanium, A.Rawat, A.Mukerjee,“A robot that learns to play soccer”, Proc. Intl. Symp. on Intelligent Robotic Systems, Ed. M. Vidyasagar, January 1998.

Peer-Reviewed, Non-Archived Conference and Workshop Papers 

• • [RL] A Gupta, Rahul Jain, Peter Glynn, “Probabilistic Contraction Analysis of Iterated Random Operators”, INFORMS Applied Probability Society Meeting, July 2019. 

  • [RL] H Sharma, William Haskell and Rahul Jain, “An Empirical Algorithm for Solving Continuous State Space MDPs”, ITA Workshop, February 2019. (invited). 

  • [RL] Mukul Gagrani*, Rahul Jain, Ashutosh Nayyar and Yi Ouyang*,“Learning to control unknown stochastic systems”, ITA Workshop, February 2018.(invited).

  • [RL] Mukul Gagrani*,Rahul Jain, Ashutosh Nayyar and Yi Ouyang*,“Learning to control unknown systems”, Simons Institute Workshop on Societal Networks, March 2018.(invited). 2017: 

  • [QT] M. Jafarnia* and Rahul Jain, “Non-indexability of the Stochastic Appointment Scheduling Problem”, INFORMS Applied Probability Society Meeting, July 2017. 

  • [SC] William Haskell and Rahul Jain, “A Random Monotone Operator Framework for Stochastic Optimization”, INFORMS Applied Probability Society Meeting, July 2017. 

  • [SC] William B. Haskell, Rahul Jain and Hiteshi Sharma*, “The Random Monotone Operator Approach to Stochastic Optimization”, ITA Workshop, 2017. (invited) 

  • [PS] Abhishek Gupta*, Rahul Jain and Ram Rajagopal, “Pricing and Scheduling Flexible Loads”,  ITA Workshop, San Diego, Feb. 2016. (invited) 2015: 

  • [RL] William Haskell*, Rahul Jain and Dileep Kalathil*,“Empirical Methods in Control and Optimization”, IMS Workshop on Stochastic Methods in Game Theory, National University of Singapore, Nov. 2015. (invited) 

  • [QT] Harsha Honnappa*, Rahul Jain, “Transitory queueing networks”, INFORMS Applied Prob- ability Soc. Meeting, Istanbul Turkey, July 2015. 

  • [RL] Naumaan Nayyar*, Dileep Kalathil* and Rahul Jain,“Learning to Match: decentralized Learn- ing in Multi-player Multi-armed bandits”, INFORMS Applied Probability Soc. Meeting, Istanbul Turkey, July 2015. (invited) 

  • [SC] Naumaan Nayyar*, Harsha Honnappa*, Rahul Jain, “Statistical Analysis of Operating Room Schedules in Elective Surgery Hospitals”, INFORMS POMS Annual Conference, 2015 (invited session) 

  • [RL] William Haskell*, Rahul Jain and Dileep Kalathil*, “Empirical dynamic programming: Further Results”, ITA Workshop, San Diego, Feb. 2015. (invited) 

  • [PS] Wenyuan Tang* and Rahul Jain, “Equilibrium analysis of the LMP mechanism”, INFORMS Annual Meeting, San Francisco, Nov. 2014. (invited) 

  • [RL] William Haskell*, Dileep Kalathil* and Rahul Jain, “Empirical dynamic programming”, Banff Workshop on Optimal Cooperation, Communication, and Learning in Decentralized Systems, Banff, AB, Oct. 2014. (invited) 

  • [QT] Harsha Honnappa*, Rahul Jain and A.Ward, “Transitory queues”,IEEE MobiHoc Workshop: Frontiers of Networks: Theory and Algorithms, Philadelphia, PA, Aug. 2014. (invited) 

  • [RL] Dileep Kalathil*, Naumaan Nayyar* and Rahul Jain, “Decentralized learning for Multi-player systems”, RSS Workshop: Humans and Sensing in Cyber-Physical Systems, Berkeley, CA, July 2014. (invited) 

  • [SC] William Haskell* and Rahul Jain, “Risk-constrained decision making”, RSS Workshop: Con- strained decision-making in robotics: models, algorithms, and applications, Berkeley, CA, July 2014. (invited) 

  • [RL] William Haskell*, Rahul Jain and Dileep Kalathil*, “Empirical dynamic programming”, ITA Workshop, San Diego, Feb. 2014. (invited) 

  • [SC] William Haskell* and Rahul Jain, “Stochastic dominance-constrained Markov decision processes”, INFORMS Computing Soc. Conf. (Computational Stochastic Optimization stream), Santa Fe, NM, Jan 2013. (invited) 

  • [PS] Wenyuan Tang* and Rahul Jain, “Market and pricing mechanisms for Smart-grid networks”, ITA Workshop, San Diego, CA, Feb. 2013. (invited) 

  • [RL] Dileep Kalathil*, Naumaan Nayyar* and Rahul Jain, “Decentralized learning for multi-player multi-armed bandits: An algorithm for near-logarithmic regret”, INFORMS Applied Probability Soc. Meeting, Costa Rica, July 2013. (invited) 

  • [QT] Harsha Honnappa* and Rahul Jain, “Timing and routing games in transitory generalized Jackson networks”, INFORMS Applied Probability Soc. Meeting, Costa Rica, July 2013. 

  • [QT] Harsha Honnappa* and Rahul Jain and A. Ward, “On fluid and diffusion Approximations for Finite Horizon Single-server Queueing Models”, INFORMS Annual Meeting, Minneapolis, MN, Oct. 2013. (invited) 

  • [SC] William Haskell*, Rahul Jain, G. Shanthikumar and Z.M.Shen, “Ambiguity in risk preferences in optimization and control”, INFORMS Annual Meeting, Minneapolis, MN, Oct. 2013. (invited) 

  • [QT] Harsha Honnappa*, Rahul Jain and Amy Ward, “The ∆(i)/GI/1 model: A new model of transitory queueing”, INFORMS Annual Meeting, Phoenix, AZ, Oct. 2012.

  • [RL] Dileep Kalathil*, Naumaan Nayyar* and Rahul Jain, “Decentralized learning for multi-player multi-armed bandits”, Information Theory and Appl. (ITA) Workshop, UCSD, Feb 2012. (invited) 

  • [QT] Harsha Honnappa*, Rahul Jain and A. Ward, “Strategically arriving users into queueing systems”, SIAM Conference on Control and its Applications, Baltimore, MD, July 2011. 

  • [GT] Dileep Kalathil* and Rahul Jain, “Communication games on the generalized Gaussian relay channel”, Information Theory and Appl. (ITA) Workshop, UCSD, Feb 2011. (invited) 

  • [RL] Rahul Jain, “Solving Markov decision problems via simulations”, International Congress of Mathematicians (ICM) Satellite Conf. on Probability and Stochastic Processes, Bangalore, India, Aug. 2010. 

  • [QT] Rahul Jain, Sandeep Juneja and Nahum Shimkin, “The concert queueing game: To wait or to be late”, Information Theory and Appl. (ITA) Workshop, UCSD 2010 (invited). 

  • [QT] Harsha Honnappa* and Rahul Jain, “Strategic arrivals into queueing networks”, INFORMS Annual Meeting, Austin, TX, Nov 2010. 

  • [QT] Rahul Jain and Sandeep Juneja, “The concert queueing problem: A game of arrivals”, INFORMS Applied Probability Society Conference, Ithaca, NY, July 2009.

  • [SC] Rahul Jain and Vivek Borkar, “Risk-constrained Markov decision processes”, INFORMS Applied Probability Society Conference, Ithaca, NY, July 2009.

  • [SC] Vivek Borkar and Rahul Jain,“Markov decision processes with CVAR constraints”,INFORMS Annual Meeting, San Diego, CA, October 2009. 2008-07: 

  • [QT] Rahul Jain and Parijat Dube, “ N-player queueing games: Pricing competition for queued services”, Information Theory and Applications (ITA) Workshop, UCSD, January 2008 (invited). 

  • [GT] Rahul Jain, “Stability of marriage and dowry”, Intl. Conf. on Applied Mathematics, Plovdiv, Bulgaria, August 2007. 

  • [GT] Rahul Jain,“A design for an asymptotically efficient combinatorial Bayesian markets: Generalizing the Satterthwaite-Williams mechanism”, Int. Conf. on Game Theory, Stony Brook, NY, July 2007. 

  • [QT] Parijat Dube and Rahul Jain, “Pricing differentiated queued services”, INFORMS Annual Meeting, , Seattle, WA, November 2007. (invited) 

  • [QT] Parijat Dube, Rahul Jain and C. Touati, “An analysis of oligopolistic competitive markets of queued services with QoS guarantees” INFORMS Applied Probability Meeting, Eindhoven, The Netherlands, July 2007. 

  • [RL] RahulJain and Pravin Varaiya, “Simulation-based optimization for Markov decision processes and Multi-armed bandits: An empirical process theory approach, Conf. on Stochastic Processes and Applications (SPA-07), Urbana-Champaign, IL, August 2007. 

  • [RL] Rahul Jain and Pravin Varaiya, “Simulation-based uniform estimates of value functions of Markov decision processes”, Conf. Stochastic Processes and Applications (SPA-05), Santa Barbara, CA, June 2005. 

  • [CN] Rahul Jain, “Geographical routing for wireless ad hoc networks”, IMA Workshop on Hot Topics in Wireless, University of Minnesota, Minneapolis, August 2001. (invited) 

  • [CN] Rahul Jain, “Geographical routing for wireless ad hoc networks using partial information”, Workshop on The Foundations of Wireless Networks and Applications, DIMACS Center, Rutgers University and AT&T Shannon Labs, August 2000. (invited)
    
    

Dissertation

•  Efficient Market Mechanisms and Simulation-based Learning for Multi-Agent Systems, Ph.D. dissertation, EECS Department, University of California, Berkeley, December 2004.   

(Advisor: Prof. Pravin Varaiya)

Patents

• R. Jain, C.Kaskiris, N.Pillai, R.Rajagopal, J.Shu and P.P.Varaiya, “System and method for conducting combinatorial exchanges”, US Provisional Patent: 60/665058, March 23, 2005. (US Patent application file: 11/389558), March 23, 2006. 

• R. Jain, “Method and system for designing bipartite matching markets with applications to online advertising industry”, US patent application file: 11/837616, filed August 13, 2007.    

• R. Jain and P. Dube, “A method and system for auction of assets with non-exclusivity of use”, US Patent application file: 12/164207, filed June 2008. 

• P. Dube and R. Jain, “Incentivized reputation-based knowledge exchange”, US Patent application file: 12/147994, filed June 2008.

• R. Jain, P. Dube and M. Naphade, “Collaborative networking with optimized information quality assessment”, US Patent application file: 20110208684, filed Feb 22, 2010.

• P. Dube, R. Jain and M. Naphade, “Collaborative networking with optimized inter-domain information quality assessment”, US Patent application file: 20110208687, filed Feb 22, 2010.

• P. Dube, R. Jain, R. Kannan and K. Subbian, “Method and system for user guided search navigation”, US Patent application file: 20110078140, filed: Sep 25, 2009

• P. Chowdhury, A. Gupta, R. Jain, J. Kalagnanam, S. Siegel and D. Subramanian, “Developing an optimal long term electricity generation capacity resource plan under a Carbon dioxide regulatory regime”, US Patent application file: 20110178833, filed: Jan. 20, 2010

• R. Jain, P. Dube and S. Sahu, “Method and system for location-aware user specific advertise- ments”, US Patent application file: 20110082752, filed: Oct. 2, 2009.

• *denotes student or mentee author

Disclaimer: The copyrights of the papers belong to the publishers. The papers are made available here for your convenience.