Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

2020-07-06 · ICML 2020 1 · Silviu Pitis, Harris Chan, Stephen Zhao, Bradly Stadie, Jimmy Ba

What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not pursue unobtainable goals. Instead, it should set its own intrinsic goals that maximize the entropy of the historical achieved goal distribution. We propose to optimize this objective by having the agent pursue past achieved goals in sparsely explored areas of the goal space, which focuses exploration on the frontier of the achievable goal set. We show that our strategy achieves an order of magnitude better sample efficiency than the prior state of the art on long-horizon multi-goal tasks including maze navigation and block stacking.

📄 PDF Abstract BibTeX arXiv:2007.02832

Code (2)

spitis/mrl 공식 구현 pytorch

penn-pal-lab/peg tf

Tasks

Multi-Goal Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Deep exploration by novelty-pursuit with maximum state entropy

2019-09-25 · Zi-Niu Li, Xiong-Hui Chen, Yang Yu

Efficient exploration is essential to reinforcement learning in huge state space. Recent approaches to address this issue include the intrinsically motivated goal exploration process (IMGEP) and the maximum state entropy…

Efficient Exploration MuJoCo

Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate

2020-07-09 · Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli

In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy? In this paper, we argue that the entropy of the state distribu…

continuous-control Continuous Control

A Policy Gradient Method for Task-Agnostic Exploration

2020-06-12 · ICML Workshop LifelongML 2020 7 · Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli

continuous-control Continuous Control

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy

2024-12-05 · Hongming Li, Shujian Yu, Bin Liu, Jose C. Principe

This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that is able to explore environments without …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

2026-03-13 · Jun Xue, Junze Wang, Shanze Wang, Xinming Zhang 외 arxiv

Scaling Maximum Entropy Reinforcement Learning (RL) to high-dimensional humanoid control remains a fundamental challenge, as the ''curse of dimensionality'' induces severe exploration inefficiency and training instabilit…

Reinforcement Learning Continuous Control