The paper investigates whether the policy gradient update used in many reinforcement learning algorithms—specifically the episode-summed, on‑policy update that omits the outer discount factor—can be interpreted as the gradient of any objective function. The authors prove that this update does not necessarily correspond to the gradient of any function and provide a counterexample where the update drives the policy toward a globally pessimal deterministic limit while the parameters diverge. They also highlight that this theoretical ambiguity has led to widespread misstatements in the literature, even in highly cited works from top conferences.
By Chris Nota, Philip S. Thomas
arXiv:2505. 03155v2 Announce Type: replace Abstract: Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning.
By Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvari, Sharan Vaswani
arXiv:2506. 13862v2 Announce Type: replace-cross Abstract: In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in theory and practice.
By Alex Davey, Alena Shilova, Brahim Driss, Riad Akrour
The paper introduces Fast Regularized Policy Mirror Descent (PMD) that pairs policy updates with a single temporal-difference (TD) critic step. It proves global linear convergence for finite discounted MDPs using exact coordinate-wise Bellman updates and any positive actor stepsize, regardless of critic initialization. For stochastic TD-PMD with strongly convex mirror maps, the authors achieve an expected value gap of ε after “~O(1/((1-γ)^5 σ_b ε))” transitions, without requiring trajectory resets, generative models, or nested policy evaluation loops.
By Qipei Chen, Wenye Li, Yule Sun, Ke Wei
arXiv:2605. 05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy.
By Dillon Sandhu, Ronald Parr
The paper introduces Loopless Variance-Reduced Policy Gradient (LVR-PG), a framework that unifies first‑order estimators combining recursive updates with defensive importance sampling, such as PAGE-PG and STORM-PG. It proves that LVR-PG achieves a ∫O(ε⁻²) last‑iterate global convergence rate under weak gradient domination for general parametric policies, using only first‑order updates and minimal assumptions. By extending lower bounds to continuous parametric policies, the authors show an Ω(ε⁻²) sample complexity limit, establishing that LVR-PG is minimax‑optimal up to logarithmic factors and horizon terms.
By Leonardo Cesani, Matteo Papini, Marcello Restelli
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: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
arXiv:2602. 09300v2 Announce Type: replace Abstract: We consider the policy evaluation and control in a finite horizon reinforcement learning (RL) setting under an expectile-based objective.
By Shrey Rakeshkumar Patel, Sumedh Gupte, Soumen Pachal, Prashanth L. A., Sanjay P. Bhat
arXiv:2609.36945v1 Announce Type: new
Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...
By Zhiwei Wang, Yanxi Chen, Yaliang Li, Bolin Ding
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.
By Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal
arXiv:2605.06149v2 Announce Type: replace-cross
Abstract: The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep R...
By Yaomin Wang, Jianting Pan, Ran Tian, Xiaoyang Li, Yu Zhang, Hengle Qin, Tianshu YU