paper-with-me

Papers

Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods

2019-12-11 · Riashat Islam, Raihan Seraj, Pierre-Luc Bacon, Doina Precup

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be uniformly optimal for others, no matter where the agent starts from. Furthermore, to obtain unbiased gradient estimates, the starting point of the policy gradient estimator requires sampling states from a normalized discounted weighting of states. However, the difficulty of estimating the normalized discounted weighting of states, or the stationary state distribution, is quite well-known. Additionally, the large sample complexity of policy gradient methods is often attributed to insufficient exploration, and to remedy this, it is often assumed that the restart distribution provides sufficient exploration in these algorithms. In this work, we propose exploration in policy gradient methods based on maximizing entropy of the discounted future state distribution. The key contribution of our work includes providing a practically feasible algorithm to estimate the normalized discounted weighting of states, i.e, the \textit{discounted future state distribution}. We propose that exploration can be achieved by entropy regularization with the discounted state distribution in policy gradients, where a metric for maximal coverage of the state space can be based on the entropy of the induced state distribution. The proposed approach can be considered as a three time-scale algorithm and under some mild technical conditions, we prove its convergence to a locally optimal policy. Experimentally, we demonstrate usefulness of regularization with the discounted future state distribution in terms of increased state space coverage and faster learning on a range of complex tasks.

📄 PDF Abstract BibTeX arXiv:1912.05104

Code (0)

등록된 구현이 없습니다.

Tasks

Policy Gradient Methods

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음

Similar Papers 제목 키워드 기반

Marginalized State Distribution Entropy Regularization in Policy Optimization

2019-12-11 · Riashat Islam, Zafarali Ahmed, Doina Precup

Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stoch…

continuous-controlContinuous ControlReinforcement Learning

Maximum-Entropy Exploration with Future State-Action Visitation Measures

2026-03-19 · Adrien Bolland, Gaspard Lambrechts, Damien Ernst arxiv

Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewards proportional to that entropy functio…

Reinforcement Learning

Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures

2024-12-09 · Adrien Bolland, Gaspard Lambrechts, Damien Ernst

We introduce a new maximum entropy reinforcement learning framework based on the distribution of states and actions visited by a policy. More precisely, an intrinsic reward function is added to the reward function of the…

reinforcement-learningReinforcement Learning

Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes

2024-06-06 · Johannes Müller, Semih Cayci

We study the error introduced by entropy regularization in infinite-horizon, discrete, discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength both in …

Policy Gradient Methods

Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime

2020-10-22 · ICLR 2021 1 · Andrea Agazzi, Jianfeng Lu

We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on th…