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.
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.
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...
arXiv:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).
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...
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.
arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).
arXiv:2602. 05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy optimization.
arXiv:2608.24146v1 Announce Type: new Abstract: In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate...
In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been propo...
The paper introduces Dissimilarity-based Markov Decision Processes (DMDPs) to learn policies that stabilize state distributions in stochastic systems. It provides a theoretical framework, finite-dimensional distribution representation, and stability certificates that account for learning and estimation errors. Practical algorithms combine distribution estimates with PPO and SAC, demonstrated on a linear system and a HalfCheetah task to regulate velocity distributions.
Limiting‑Kernel Q(λ) (LKQL) is an off‑policy value estimator that blends n‑step truncation with a long‑horizon approximation based on the limiting kernel. It maintains the computational efficiency of n‑step methods while improving policy evaluation accuracy, especially for long‑horizon tasks. The authors prove faster convergence of LKQL’s operator under aperiodicity and near‑on‑policy conditions, and demonstrate empirical gains on MuJoCo continuous‑control benchmarks.
arXiv:2606. 11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training.