arXiv Machine Learning June 2, 2026 By Haoyu Han, Heng Yang

Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

Read the original on arXiv Machine Learning →

arXiv:2602. 01460v3 Announce Type: replace-cross Abstract: Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv AI

Jun 6

Retry Policy Gradients in Continuous Action Spaces

arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.

By Soichiro Nishimori, Paavo Parmas

arXiv Machine Learning

Oct 5

Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds

arXiv:2610.03165v1 Announce Type: new Abstract: Several variance-reduced versions of REINFORCE based on importance sampling achieve an improved $O(\epsilon^{-3})$ sample complexity to find an $\epsil...

By Gabor Paczolay, Matteo Papini, Alberto Maria Metelli, Istvan Harmati, Marcello Restelli

reinforcement-learning

arXiv AI

Jul 14

Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning

arXiv:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).

By Yang Xu, Swetha Ganesh, Vaneet Aggarwal

reinforcement-learning

arXiv Machine Learning

1d ago

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

arXiv:2503.22244v3 Announce Type: replace Abstract: Policy gradient methods are among the most successful approaches for solving challenging reinforcement learning problems. Despite their empirical s...

By Weizhen Wang, Xinzhe Zhou, Jianping He, Xiaoming Duan

reinforcement-learning benchmarks

arXiv AI

Jun 19

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

arXiv:2601. 22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment.

By Jeong Woon Lee, Kyoleen Kwak, Daeho Kim, Hyoseok Hwang

arXiv AI

Jul 10

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition

arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).

By Sanjeev Manivannan, Shuban V

reinforcement-learning

One email a morning, machine-written

Related stories

Retry Policy Gradients in Continuous Action Spaces

Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds

Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition