2021-07-01-amin21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards	A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action spaces. Intuitively, if the reinforcement signal is very scarce, the agent should rely on some form of short-term memory in order to cover its environment efficiently. We propose a new exploration method, based on two intuitions: (1) the choice of the next exploratory action should depend not only on the (Markovian) state of the environment, but also on the agent’s trajectory so far, and (2) the agent should utilize a measure of spread in the state space to avoid getting stuck in a small region. Our method leverages concepts often used in statistical physics to provide explanations for the behavior of simplified (polymer) chains in order to generate persistent (locally self-avoiding) trajectories in state space. We discuss the theoretical properties of locally self-avoiding walks and their ability to provide a kind of short-term memory through a decaying temporal correlation within the trajectory. We provide empirical evaluations of our approach in a simulated 2D navigation task, as well as higher-dimensional MuJoCo continuous control locomotion tasks with sparse rewards.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	amin21a	0	Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards	275	285	275-285	275	false	Amin, Susan and Gomrokchi, Maziar and Aboutalebi, Hossein and Satija, Harsh and Precup, Doina	given family Susan Amin given family Maziar Gomrokchi given family Hossein Aboutalebi given family Harsh Satija given family Doina Precup	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/amin21a/amin21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/amin21a/amin21a-supp.pdf