arXiv Machine Learning June 25, 2026 By Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal

Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL

Read the original on arXiv Machine Learning →

arXiv:2606. 25012v1 Announce Type: new Abstract: Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 31

Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs

arXiv:2607. 28390v1 Announce Type: new Abstract: Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maximize long-term reward while satisfying long-term constraints.

By Ankur Naskar, Vaneet Aggarwal

agents reinforcement-learning safety

arXiv AI

Jun 17

Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning

arXiv:2606. 18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives.

By Umer Siddique, Peilang Li, Yongcan Cao

reinforcement-learning benchmarks safety

arXiv AI

Jun 11

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

arXiv:2505. 15201v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently.

By Christian Walder, Deep Karkhanis

llms reinforcement-learning

arXiv AI

Jul 3

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

arXiv:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.

By Anish Diwan, Davide Tateo, Christopher E. Mower, Haitham Bou-Ammar, Jan Peters, Oleg Arenz

reinforcement-learning benchmarks safety

arXiv Machine Learning

Aug 4

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

arXiv:2608. 02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints.

By Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner

rag reinforcement-learning benchmarks

arXiv Machine Learning

Aug 12

Boundary-Seeking Policy Gradient for Safe Reinforcement Learning

arXiv:2608. 10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints.

By Chenhua Fan, Jiahui Zhu, Yuhang Zhang, Honghao Wei

reinforcement-learning safety

Related stories

Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs

Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

Boundary-Seeking Policy Gradient for Safe Reinforcement Learning