Akshat Kumar's Publications

Refereed Journal/Conference Publications

• Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal Dataset
  Quang Anh Pham, Tien Mai, and Akshat Kumar.
  In International Conference on Machine Learning (ICML), 2026.

• TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels
  Siow Meng Low, Ze Gong, and Akshat Kumar.
  In International Conference on Machine Learning (ICML), 2026.

• Persistent Safety Set Guided Offline Safe Reinforcement Learning
  Ayan Roy Choudhury, Janaka Brahmanage, Akshat Kumar, and Praveen Paruchuri.
  In International Joint Conference on Artificial Intelligence (IJCAI), 2026.

• Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
  Janaka Brahmanage and Akshat Kumar.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2026.

• Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning
  Janaka Brahmanage, Jiajing Ling, and Akshat Kumar.
  In AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Offline Safe Reinforcement Learning Using Trajectory Classification
  Ze Gong, Akshat Kumar, and Pradeep Varakantham.
  In AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Adaptive Moving Target Defense in Web Applications and Networks using Factored MDP
  Megha Bose, Praveen Paruchuri, and Akshat Kumar.
  In International Conference on COMmunication Systems & NETworkS (COMSNETS), 2025.

• ShipNaviSim: Data-Driven Simulation for Real-World Maritime Navigation
  Quang Anh Pham, Janaka Chathuranga Brahmanage, and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2025.

• Factored MDP based Moving Target Defense with Dynamic Threat Modeling
  Megha Bose, Praveen Paruchuri, and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.

• Difference of Convex Functions Programming for Policy Optimization in Reinforcement Learning
  Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.

• Unified Training of Universal Time Series Forecasting Transformers
  Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, and Doyen Sahoo.
  In International Conference on Machine Learning (ICML), 2024.

• Scalable and Globally Optimal Generalized L₁ K-center Clustering via Constraint Generation in Mixed Integer Linear Programming
  Aravinth Chembu, Scott Sanner, Hassan Khurram, and Akshat Kumar.
  In AAAI Conference on Artificial Intelligence (AAAI), 2023.

• Planning and Learning for Non-markovian Negative Side Effects Using Finite State Controllers
  Aishwarya Srivastava, Sandhya Saisubramanian, Praveen Paruchuri, Akshat Kumar, and Shlomo Zilberstein.
  In AAAI Conference on Artificial Intelligence (AAAI), 2023.

• Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects
  Siow Meng Low, Akshat Kumar, and Scott Sanner.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2023.

• Knowledge Compilation for Constrained Combinatorial Action Spaces in Reinforcement Learning
  Jiajing Ling, Moritz Lukas Schuler, Akshat Kumar, and Pradeep Varakantham.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.

• A Mixed-Integer Linear Programming Reduction of Disjoint Bilinear Programs via Symbolic Variable Elimination
  Jihwan Jeong, Scott Sanner, and Akshat Kumar.
  In International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR), 2023.

• Learning Deep Time-index Models for Time Series Forecasting
  Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, and Steven C. H. Hoi.
  In International Conference on Machine Learning (ICML), 2023.

• FlowPG: Action-constrained Policy Gradient with Normalizing Flows
  Janaka Chathuranga Brahmanage, Jiajing Ling, and Akshat Kumar.
  In Conference on Neural Information Processing Systems (NeurIPS), 2023.

• Constrained Multiagent Reinforcement Learning for Large Agent Population
  Jiajing Ling, Arambam James Singh, Nguyen Duc Thien, and Akshat Kumar.
  In European Conference on Machine Learning (ECML), 2022.

• Trajectory Optimization for Safe Navigation in Maritime Traffic Using Historical Data
  Chaithanya Basrur, Arambam James Singh, Arunesh Sinha, Akshat Kumar and T. K. Satish Kumar.
  In International Conference on Principles and Practice of Constraint Programming (CP), 2022.

• Using Constraint Programming and Graph Representation Learning for Generating Interpretable Cloud Security Policies
  Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar.
  In International Joint Conference on Artificial Intelligence (IJCAI), 2022.

• Sample-efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs
  Siow Meng Low, Akshat Kumar, Scott Sanner.
  In AAAI Conference on Artificial Intelligence (AAAI), 2022.

• CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
  Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi.
  In International Conference on Learning Representation (ICLR), 2022.

• Action Selection For Composable Modular Deep Reinforcement Learning
  Vaibhav Gupta, Daksh Anand, Praveen Paruchuri, Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021.

• Integrating Knowledge Compilation with Reinforcement Learning for Routes
  Jiajing Ling, Kushagra Chandak, Akshat Kumar.
  International Conference on Automated Planning and Scheduling (ICAPS), 2021.

• Learning and Exploiting Shaped Reward Models for Large Scale Multiagent RL
  Arambam James Singh, Akshat Kumar, Hoong Chuin Lau.
  International Conference on Automated Planning and Scheduling (ICAPS), 2021.

• Ship-GAN: Generative Modeling Based Maritime Traffic Simulator
  Chaithanya Basrur, Arambam James Singh, Arunesh Sinha and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021. Best Demo Award

• Approximate Difference Rewards for Scalable Multigent Reinforcement Learning
  Arambam James Singh, Akshat Kumar, Hoong Chuin Lau.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021.

• Reinforcement Learning for Zone Based Multiagent Pathfinding under Uncertainty
  Jiajing Ling, Tarun Gupta, Akshat Kumar.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2020.

• Hierarchical Multiagent Reinforcement Learning for Maritime Traffic Management
  Arambam James Singh, Akshat Kumar, Hoong Chuin Lau.
  International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020.

• Multiagent Decision Making and Learning in Urban Environments
  Akshat Kumar.
  International Joint Conference on Artificial Intelligence (IJCAI), Early Career Invited Paper, 2019.

• Decision Making for Improving Maritime Traffic Safety Using Constraint Programming
  S. Bhatnagar, A Kumar, HC Lau.
  International Joint Conference on Artificial Intelligence (IJCAI), 2019.

• Resource Constrained Deep Reinforcement Learning
  Abhinav Bhatia, Pradeep Varakantham, Akshat Kumar.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2019.

• Graph Based Optimization For Multiagent Cooperation
  Arambam James Singh, Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019.

• Successor Features Based Multi-Agent RL for Event-Based Decentralized MDPs
  Tarun Gupta, Akshat Kumar and Praveen Paruchuri.
  AAAI Conference on Artificial Intelligence (AAAI), 2019.

• Multiagent Decision Making For Maritime Traffic Management
  Arambam james Singh, Duc Thien Nguyen, Akshat Kumar and Hoong Chuin Lau.
  AAAI Conference on Artificial Intelligence (AAAI), 2019.

• Credit Assignment For Collective Multiagent RL With Global Rewards
  Duc Thien Nguyen, Akshat Kumar and Hoong Chuin Lau.
  International Conference on Neural Information Processing Systems (NeurIPS), 2018.

• Planning and Learning For Decentralized MDPs with Event Driven Rewards
  Tarun Gupta, Akshat Kumar and Praveen Paruchuri.
  AAAI Conference on Artificial Intelligence (AAAI), 2018.

• Resource Constrained Scheduling for Maritime Traffic Management
  Lucas Agussurja, Akshat Kumar and HC Lau.
  AAAI Conference on Artificial Intelligence (AAAI), 2018.

• Integrated Cooperation and Competition in Multi-Agent Decision-Making
  Kyle H. Wray, Akshat Kumar and Shlomo Zilberstein.
  AAAI Conference on Artificial Intelligence (AAAI), 2018.

• Policy Gradient With Value Function Approximation For Collective Multiagent Planning
  Duc Thien Nguyen, Akshat Kumar and Hoong Chuin Lau.
  International Conference on Neural Information Processing Systems (NIPS), 2017.

• Collective Multiagent Sequential Decision Making Under Uncertainty
  Duc Thien Nguyen, Akshat Kumar and Hoong Chuin Lau.
  AAAI Conference on Artificial Intelligence (AAAI), 2017.

• Decentralized Planning in Stochastic Environments with Submodular Rewards
  Rajiv Ranjan Kumar, Pradeep Varakantham and Akshat Kumar.
  AAAI Conference on Artificial Intelligence (AAAI), 2017.

• Robust Optimization for Tree-Structured Stochastic Network Design
  Xiaojian Wu, Akshat Kumar, Daniel Sheldon, and Shlomo Zilberstein.
  AAAI Conference on Artificial Intelligence (AAAI), 2017. Best Paper Award, CompSust track

• Risk-Sensitive Stochastic Orienteering Problems for Trip Optimization in Urban Environments
  Pradeep Varakantham, Akshat Kumar, HC Lau and William Yeoh.
  In ACM Transactions on Intelligent Systems and Technology (TIST), 2017.

• Coordinating Vessel Traffic To Improve Safety and Efficiency
  Teng Teck Hou, Hoong Chuin Lau, and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2017.

• Multiagent Coordination Using Graph Structured Mathematical Optimization (Extended Abstract)
  Arambam James Singh and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2017.

• Shortest Path Based Decision Making Using Probabilistic Inference
  Akshat Kumar.
  AAAI Conference on Artificial Intelligence (AAAI), 2016.

• Robust Decision Making For Stochastic Network Design
  Akshat Kumar, Arambam James Singh, Pradeep Varakantham and Daniel Sheldon.
  AAAI Conference on Artificial Intelligence (AAAI), 2016.

• Dual Formulations for Optimizing Dec-POMDP Controllers
  Akshat Kumar, Hala Mostafa, and Shlomo Zilberstein.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2016.

• Approximate Inference Using DC Programming For Collective Graphical Models
  Thien Nguyen, Akshat Kumar, Hoong Chuin Lau, and Daniel Sheldon.
  In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.

• Robust Influence Maximization (Extended Abstract)
  Meghna Lowalekar, Pradeep Varakantham, and Akshat Kumar.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2016.

• Probabilistic Inference Techniques for Scalable Multiagent Decision Making
  Akshat Kumar, Marc Toussaint, and Shlomo Zilberstein.
  In Journal of Artificial Intelligence Research (JAIR), 2015.

• History-Based Controller Design and Optimization for Partially Observable MDPs
  Akshat Kumar and Shlomo Zilberstein.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2015.

• Probabilistic Inference Based Message-Passing For Resource Constrained DCOPs
  Supriyo Ghosh, Akshat Kumar and Pradeep Varakantham.
  In International Joint Conference on Artificial Intelligence (IJCAI), 2015.

• Message Passing For Collective Graphical Models
  Tao Sun, Daniel Sheldon and Akshat Kumar.
  In International Conference on Machine Learning (ICML), 2015.

• Near-Optimal Decentralized Power Supply Restoration in Smart Grids
  Pritee Agarwal, Akshat Kumar, Pradeep Varakantham.
  In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015

• Decomposition Techniques for Urban Consolidation Problems
  Duc Thien Nguyen, Hoong Chuin Lau and Akshat Kumar.
  In the IEEE International Conference on Automation Science and Engineering (IEEE CASE), 2015

• Learning and Controlling Network Diffusion in Dependent Cascade Models
  Jiali Du, Pradeep Varakantham, Akshat Kumar and Shih-Fen Cheng.
  In the IEEE Intelligent Agent Conference (IAT), 2015

• Near-Optimal Nonmyopic Contact Center Planning Using Dual Decomposition
  Akshat Kumar, Sudhanshu Singh, Pranav Gupta and Gyana Parija.
  In International Conference on Automated Planning and Scheduling (ICAPS), 2014. Best Application Paper Award

• On Understanding Diffusion Dynamics of Patrons at a Theme Park (Extended Abstract)
  Jiali Du, Akshat Kumar, Pradeep Varakantham.
  International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2014.

• Optimization Approaches for Solving Chance Constrained Stochastic Orienteering Problems
  Pradeep Varakantham, Akshat Kumar.
  Accepted in the International Conference on Algorithmic Decision Theory (ADT), 2013.

• Collective Diffusion Over Networks: Models and Inference.
  Akshat Kumar, Daniel Sheldon and Biplav Srivastava.
  Accepted in the International Conference on Uncertainty in Artificial Intelligence (UAI), 2013.

• Approximate Inference in Collective Graphical Models.
  Daniel Sheldon, Tao Sun, Akshat Kumar and Thomas G. Dietterich.
  Accepted in the International Conference on Machine Learning (ICML), 2013.

• Parameter Learning for Latent Network Diffusion.
  Xiaojian Wu, Akshat Kumar, Daniel Sheldon and Shlomo Zilberstein.
  Accepted in the International Joint Conference on Artificial Intelligence (IJCAI), 2013.

• Automated Generation of Interaction Graphs for Value-Factored Decentralized POMDPs.
  William Yeoh, Akshat Kumar and Shlomo Zilberstein.
  In International Joint Conference on Artificial Intelligence (IJCAI), 2013.

• Lagrangian Relaxation Techniques for Scalable Spatial Conservation Planning.
  Akshat Kumar, Xiaojian Wu and Shlomo Zilberstein.
  Accepted in the AAAI Conference on Artificial Intelligence (AAAI), 2012.

• Message Passing Algorithms for MAP Estimation Using DC Programming.
  Akshat Kumar, Shlomo Zilberstein and Marc Toussaint.
  In Proc. of the International Conference on Artificial Intelligence and Statistics (AISTATS), pages 656-664, 2012.

• Message-Passing Algorithms for Quadratic Programming Formulations of MAP Estimation.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Uncertainty in Artificial Intelligence (UAI), pages 428-435, 2011.

• Scalable Multiagent Planning using Probabilistic Inference.
  Akshat Kumar, Shlomo Zilberstein and Marc Toussaint.
  In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), pages 2140-2146, 2011.

• Influence Diagrams With Memory States: Representation and Algorithms.
  Xiaojian Wu, Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Algorithmic Decision Theory (ADT), pages 306-319, 2011.

• Message-Passing Algorithms for Large Structured Decentralized POMDPs.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1087-1088, 2011.

• MAP Estimation for Graphical Models by Likelihood Maximization.
  Akshat Kumar and Shlomo Zilberstein.
  In Advances in Neural Information Processing Systems (NIPS), pages 1180-1188, 2010.

• Anytime Planning for Decentralized POMDPs using Expectation Maximization.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Uncertainty in Artificial Intelligence (UAI), pages 294-301, 2010.

• Point-Based Backup for Decentralized POMDPs: Complexity and New Algorithms.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1315-1322, 2010.

• Event-detecting Multi-agent MDPs: Complexity and Constant-Factor Approximation.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), pages 201-207, 2009.

• Constraint-Based Dynamic Programming for Decentralized POMDPs with Structured Interactions.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 561-568, 2009.

• Distributed Constraint Optimization with Structured Resource Constraints.
  Akshat Kumar, Boi Faltings and Adrian Petcu.
  In Proc. of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 923-930, 2009.

• Dynamic Programming Approximations for Partially Observable Stochastic games.
  Akshat Kumar and Shlomo Zilberstein.
  In Proc. of the FLAIRS Conference, pages 547-552, 2009.

• H-DPOP: Using Hard Constraints for Search Space Pruning in DCOP.
  Akshat Kumar, Adrian Petcu and Boi Faltings.
  In Proc. of the AAAI Conference on Artificial Intelligence (AAAI), pages 325-330, 2008.

• An Artificial Immune System based Approach for English Grammar Correction.
  Akshat Kumar and Shivsankar Nair.
  In Proc. of the International Conference on Artificial Immune Systems (ICARIS), pages 348-357, 2007.

• Tournament versus Fitness Uniform Selection.
  Shane Legg Legg, Marcus Hutter and Akshat Kumar.
  In Proc. of the IEEE Congress on Evolutionary Computation (CEC), pages 2144-2151, 2004.