English
Related papers

Related papers: Overcoming Valid Action Suppression in Unmasked Po…

200 papers

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is formulated theoretically as the expected returns discounted…

Machine Learning · Computer Science 2023-02-13 Haoxuan Pan , Deheng Ye , Xiaoming Duan , Qiang Fu , Wei Yang , Jianping He , Mingfei Sun

A key capability of intelligent agents is operating under partial observability: reasoning and acting effectively despite missing or incomplete state observations. While recurrent (memory-based) policies learned via reinforcement learning…

Machine Learning · Computer Science 2026-05-12 David Leeftink , Max Hinne , Marcel van Gerven

Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a…

Robotics · Computer Science 2022-11-11 Hai Nguyen , Andrea Baisero , Dian Wang , Christopher Amato , Robert Platt

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…

Machine Learning · Computer Science 2026-05-12 Avik Kar , Siddharth Chandak , Rahul Singh , Soumitra Sinhahajari , Eric Moulines , Shalabh Bhatnagar , Nicholas Bambos

Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity,…

Cryptography and Security · Computer Science 2024-05-14 Zhixiong Zhuang , Maria-Irina Nicolae , Mario Fritz

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…

Machine Learning · Computer Science 2023-09-26 Nirbhay Modhe , Qiaozi Gao , Ashwin Kalyan , Dhruv Batra , Govind Thattai , Gaurav Sukhatme

This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design…

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

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy…

Computation and Language · Computer Science 2026-05-13 Yuxiang Ji , Zengbin Wang , Yong Wang , Shidong Yang , Ziyu Ma , Guanhua Chen , Zonghua Sun , Liaoni Wu , Xiangxiang Chu

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the theoretical foundations of learning a good policy from…

Machine Learning · Computer Science 2026-05-11 Xiang Li , Yuheng Zhang , Nan Jiang

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability.…

Deep reinforcement learning was instigated with the presence of trust region methods, being scalable and efficient. However, the pessimism of such algorithms, among which it forces to constrain in a trust region by all means, has been…

Machine Learning · Computer Science 2023-03-06 Jianfei Ma

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional…

Machine Learning · Computer Science 2018-03-21 Cathy Wu , Aravind Rajeswaran , Yan Duan , Vikash Kumar , Alexandre M Bayen , Sham Kakade , Igor Mordatch , Pieter Abbeel

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies.…

Machine Learning · Computer Science 2020-08-14 Alekh Agarwal , Mikael Henaff , Sham Kakade , Wen Sun

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

In reinforcement learning, the softmax parametrization is the standard approach for policies over discrete action spaces. However, it fails to capture the order relationship between actions. Motivated by a real-world industrial problem, we…

Machine Learning · Computer Science 2025-06-24 Simón Weinberger , Jairo Cugliari

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Machine Learning · Computer Science 2025-06-16 Miguel Suau