English
Related papers

Related papers: Actor-critic is implicitly biased towards high ent…

200 papers

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribution of the data samples dynamically changes as the model is…

Machine Learning · Computer Science 2023-09-20 Ziheng Wang , Justin Sirignano

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Machine Learning · Computer Science 2022-12-16 Md Masudur Rahman , Yexiang Xue

Deep off-policy actor-critic algorithms have emerged as the leading framework for reinforcement learning in continuous control domains. However, most of these algorithms suffer from poor sample efficiency, especially in environments with…

Machine Learning · Computer Science 2026-02-25 Zahra Shahrooei , Ali Baheri

We study sequential decision-making when the agent's internal model class is misspecified. Within the infinite-horizon Berk-Nash framework, stable behavior arises as a fixed point: the agent acts optimally relative to a subjective model,…

Computer Science and Game Theory · Computer Science 2026-03-17 Quanyan Zhu , Zhengye Han

Sample efficiency is a critical property when optimizing policy parameters for the controller of a robot. In this paper, we evaluate two state-of-the-art policy optimization algorithms. One is a recent deep reinforcement learning method…

Machine Learning · Computer Science 2016-08-23 Arnaud de Froissard de Broissia , Olivier Sigaud

A widely-used actor-critic reinforcement learning algorithm for continuous control, Deep Deterministic Policy Gradients (DDPG), suffers from the overestimation problem, which can negatively affect the performance. Although the…

Machine Learning · Computer Science 2020-10-20 Ling Pan , Qingpeng Cai , Longbo Huang

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

We study entropy-regularized constrained Markov decision processes (CMDPs) under the soft-max parameterization, in which an agent aims to maximize the entropy-regularized value function while satisfying constraints on the expected total…

Machine Learning · Computer Science 2023-04-10 Donghao Ying , Yuhao Ding , Javad Lavaei

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

Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot…

Machine Learning · Computer Science 2019-09-10 Wenjie Shi , Shiji Song , Cheng Wu

Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We propose NAC-B, a…

Machine Learning · Computer Science 2025-10-28 Swetha Ganesh , Vaneet Aggarwal

We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…

Optimization and Control · Mathematics 2025-01-27 Mo Zhou , Jianfeng Lu

The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches such as neural density models and continuous exploration…

Machine Learning · Computer Science 2019-09-25 Bogdan Mazoure , Thang Doan , Audrey Durand , R Devon Hjelm , Joelle Pineau

The actor-critic (AC) framework has achieved strong empirical success in off-policy reinforcement learning but suffers from the "moving target" problem, where the evaluated policy changes continually. Functional critics, or…

Machine Learning · Computer Science 2026-02-10 Qinxun Bai , Yuxuan Han , Wei Xu , Zhengyuan Zhou

Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings. It uses the maximum entropy framework for efficiency and stability, and applies a heuristic temperature Lagrange term to tune the…

Machine Learning · Computer Science 2021-12-07 Yaosheng Xu , Dailin Hu , Litian Liang , Stephen McAleer , Pieter Abbeel , Roy Fox

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a…

Machine Learning · Computer Science 2020-10-21 Yuguang Yue , Zhendong Wang , Mingyuan Zhou

We revisit the standard formulation of tabular actor-critic algorithm as a two time-scale stochastic approximation with value function computed on a faster time-scale and policy computed on a slower time-scale. This emulates policy…

Machine Learning · Computer Science 2024-06-21 Shalabh Bhatnagar , Vivek S. Borkar , Soumyajit Guin

Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence on the derivative of the critic's value estimates with…

Machine Learning · Computer Science 2025-02-11 Baturay Saglam , Dionysis Kalogerias

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

Optimization and Control · Mathematics 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg
‹ Prev 1 8 9 10 Next ›