Saved in:
Bibliographic Details
Main Authors: Chitnis, Rohan, Xu, Yingchen, Hashemi, Bobak, Lehnert, Lucas, Dogan, Urun, Zhu, Zheqing, Delalleau, Olivier
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.00867
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929344487620608
author Chitnis, Rohan
Xu, Yingchen
Hashemi, Bobak
Lehnert, Lucas
Dogan, Urun
Zhu, Zheqing
Delalleau, Olivier
author_facet Chitnis, Rohan
Xu, Yingchen
Hashemi, Bobak
Lehnert, Lucas
Dogan, Urun
Zhu, Zheqing
Delalleau, Olivier
contents Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that model-based RL agents struggle in these environments due to a lack of long-term planning capabilities, and that planning in a temporally abstract model of the environment can alleviate this issue. In this paper, we make two key contributions: 1) we introduce an offline model-based RL algorithm, IQL-TD-MPC, that extends the state-of-the-art Temporal Difference Learning for Model Predictive Control (TD-MPC) with Implicit Q-Learning (IQL); 2) we propose to use IQL-TD-MPC as a Manager in a hierarchical setting with any off-the-shelf offline RL algorithm as a Worker. More specifically, we pre-train a temporally abstract IQL-TD-MPC Manager to predict "intent embeddings", which roughly correspond to subgoals, via planning. We empirically show that augmenting state representations with intent embeddings generated by an IQL-TD-MPC manager significantly improves off-the-shelf offline RL agents' performance on some of the most challenging D4RL benchmark tasks. For instance, the offline RL algorithms AWAC, TD3-BC, DT, and CQL all get zero or near-zero normalized evaluation scores on the medium and large antmaze tasks, while our modification gives an average score over 40.
format Preprint
id arxiv_https___arxiv_org_abs_2306_00867
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
Chitnis, Rohan
Xu, Yingchen
Hashemi, Bobak
Lehnert, Lucas
Dogan, Urun
Zhu, Zheqing
Delalleau, Olivier
Machine Learning
Artificial Intelligence
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that model-based RL agents struggle in these environments due to a lack of long-term planning capabilities, and that planning in a temporally abstract model of the environment can alleviate this issue. In this paper, we make two key contributions: 1) we introduce an offline model-based RL algorithm, IQL-TD-MPC, that extends the state-of-the-art Temporal Difference Learning for Model Predictive Control (TD-MPC) with Implicit Q-Learning (IQL); 2) we propose to use IQL-TD-MPC as a Manager in a hierarchical setting with any off-the-shelf offline RL algorithm as a Worker. More specifically, we pre-train a temporally abstract IQL-TD-MPC Manager to predict "intent embeddings", which roughly correspond to subgoals, via planning. We empirically show that augmenting state representations with intent embeddings generated by an IQL-TD-MPC manager significantly improves off-the-shelf offline RL agents' performance on some of the most challenging D4RL benchmark tasks. For instance, the offline RL algorithms AWAC, TD3-BC, DT, and CQL all get zero or near-zero normalized evaluation scores on the medium and large antmaze tasks, while our modification gives an average score over 40.
title IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2306.00867