Saved in:
Bibliographic Details
Main Authors: Wang, Haoran, Tang, Zeshen, Yang, Leya, Sun, Yaoru, Wang, Fang, Zhang, Siyu, Chen, Yeming
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.13508
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916197030690816
author Wang, Haoran
Tang, Zeshen
Yang, Leya
Sun, Yaoru
Wang, Fang
Zhang, Siyu
Chen, Yeming
author_facet Wang, Haoran
Tang, Zeshen
Yang, Leya
Sun, Yaoru
Wang, Fang
Zhang, Siyu
Chen, Yeming
contents Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information synchronization and cooperation by exploiting forward dynamics. Firstly, the GCMR mitigates the state-transition error within off-policy correction via model-based rollout, thereby enhancing sample efficiency. Secondly, to prevent disruption by the unseen subgoals and states, lower-level Q-function gradients are constrained using a gradient penalty with a model-inferred upper bound, leading to a more stable behavioral policy conducive to effective exploration. Thirdly, we propose a one-step rollout-based planning, using higher-level critics to guide the lower-level policy. Specifically, we estimate the value of future states of the lower-level policy using the higher-level critic function, thereby transmitting global task information downwards to avoid local pitfalls. These three critical components in GCMR are expected to facilitate inter-level cooperation significantly. Experimental results demonstrate that incorporating the proposed GCMR framework with a disentangled variant of HIGL, namely ACLG, yields more stable and robust policy improvement compared to various baselines and significantly outperforms previous state-of-the-art algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13508
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout
Wang, Haoran
Tang, Zeshen
Yang, Leya
Sun, Yaoru
Wang, Fang
Zhang, Siyu
Chen, Yeming
Machine Learning
Artificial Intelligence
Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information synchronization and cooperation by exploiting forward dynamics. Firstly, the GCMR mitigates the state-transition error within off-policy correction via model-based rollout, thereby enhancing sample efficiency. Secondly, to prevent disruption by the unseen subgoals and states, lower-level Q-function gradients are constrained using a gradient penalty with a model-inferred upper bound, leading to a more stable behavioral policy conducive to effective exploration. Thirdly, we propose a one-step rollout-based planning, using higher-level critics to guide the lower-level policy. Specifically, we estimate the value of future states of the lower-level policy using the higher-level critic function, thereby transmitting global task information downwards to avoid local pitfalls. These three critical components in GCMR are expected to facilitate inter-level cooperation significantly. Experimental results demonstrate that incorporating the proposed GCMR framework with a disentangled variant of HIGL, namely ACLG, yields more stable and robust policy improvement compared to various baselines and significantly outperforms previous state-of-the-art algorithms.
title Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2309.13508