English
Related papers

Related papers: Variance Reduction for Policy-Gradient Methods via…

200 papers

Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data…

Machine Learning · Computer Science 2022-06-16 Raghuram Bharadwaj Diddigi , Prateek Jain , Prabuchandran K. J. , Shalabh Bhatnagar

Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient methods in reinforcement learning (RL). However, the theoretical understanding of…

Machine Learning · Computer Science 2024-07-16 Yuhao Ding , Junzi Zhang , Hyunin Lee , Javad Lavaei

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In…

Machine Learning · Computer Science 2022-05-25 Prashanth L. A. , Michael Fu

We propose policy gradient algorithms for solving a risk-sensitive reinforcement learning (RL) problem in on-policy as well as off-policy settings. We consider episodic Markov decision processes, and model the risk using the broad class of…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

Machine Learning · Computer Science 2025-09-25 Guochao Jiang , Wenfeng Feng , Guofeng Quan , Chuzhan Hao , Yuewei Zhang , Guohua Liu , Hao Wang

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

Machine Learning · Computer Science 2026-02-19 Jialiang Fan , Shixiong Jiang , Mengyu Liu , Fanxin Kong

Learning to reach goal states and learning diverse skills through mutual information (MI) maximization have been proposed as principled frameworks for self-supervised reinforcement learning, allowing agents to acquire broadly applicable…

Machine Learning · Computer Science 2021-06-04 Jongwook Choi , Archit Sharma , Honglak Lee , Sergey Levine , Shixiang Shane Gu

A one-step two-critic deep reinforcement learning (OSTC-DRL) approach for inverter-based volt-var control (IB-VVC) in active distribution networks is proposed in this paper. Firstly, considering IB-VVC can be formulated as a single-period…

Artificial Intelligence · Computer Science 2022-07-04 Qiong Liu , Ye Guo , Lirong Deng , Haotian Liu , Dongyu Li , Hongbin Sun , Wenqi Huang

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout…

Machine Learning · Computer Science 2026-04-24 Yangyi Fang , Jiaye Lin , Xiaoliang Fu , Cong Qin , Haolin Shi , Chaowen Hu , Lu Pan , Ke Zeng , Xunliang Cai

Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

Optimizing static risk-averse objectives in Markov decision processes is difficult because they do not admit standard dynamic programming equations common in Reinforcement Learning (RL) algorithms. Dynamic programming decompositions that…

Optimization and Control · Mathematics 2024-07-04 Jia Lin Hau , Erick Delage , Mohammad Ghavamzadeh , Marek Petrik

This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient…

Machine Learning · Computer Science 2026-05-11 Majid Molaei , Gabor Paczolay , Matteo Papini , Alberto Maria Metelli , Marcello Restelli

Reinforcement learning constantly deals with hard integrals, for example when computing expectations in policy evaluation and policy iteration. These integrals are rarely analytically solvable and typically estimated with the Monte Carlo…

Machine Learning · Computer Science 2022-02-23 Sebastien M. R. Arnold , Pierre L'Ecuyer , Liyu Chen , Yi-fan Chen , Fei Sha

Efficient exploration for an agent is challenging in reinforcement learning (RL). In this paper, a novel actor-critic framework namely virtual action actor-critic (VAAC), is proposed to address the challenge of efficient exploration in RL.…

Machine Learning · Computer Science 2023-11-07 Bumgeun Park , Taeyoung Kim , Quoc-Vinh Lai-Dang , Dongsoo Har

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Soft actor-critic (SAC) in reinforcement learning is expected to be one of the next-generation robot control schemes. Its ability to maximize policy entropy would make a robotic controller robust to noise and perturbation, which is useful…

Machine Learning · Computer Science 2023-07-04 Taisuke Kobayashi

Many reinforcement learning methods achieve great success in practice but lack theoretical foundation. In this paper, we study the convergence analysis on the problem of the Linear Quadratic Regulator (LQR). The global linear convergence…

Optimization and Control · Mathematics 2020-07-09 Zeyu Jin , Johann Michael Schmitt , Zaiwen Wen

Traditional Reinforcement Learning (RL) policies are typically implemented with fixed control rates, often disregarding the impact of control rate selection. This can lead to inefficiencies as the optimal control rate varies with task…

Robotics · Computer Science 2024-08-13 Dong Wang , Giovanni Beltrame

Reinforcement learning (RL) is a dominant paradigm for training autonomous agents, yet these agents often exhibit poor generalization, failing to adapt to scenarios not seen during training. In this work, we identify a fundamental cause of…

Artificial Intelligence · Computer Science 2026-01-16 Jingyu Liu , Xiaopeng Wu , Jingquan Peng , Kehan Chen , Chuan Yu , Lizhong Ding , Yong Liu