Offline RL with discrete proxy representations for generalizability in POMDPs

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial...

Full description

Saved in:
Bibliographic Details
Main Authors: GU, Pengjie, CAI, Xinyu, XING, Dong, WANG, Xinrun, ZHAO, Mengchen, AN, Bo
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9048
https://ink.library.smu.edu.sg/context/sis_research/article/10051/viewcontent/Offline_rl_with_discrete_proxy_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the masked observations during execution, and ii) the information of which parts of observations are masked is usually unknown during training. In order to address these challenges, we present Offline RL with DiscrEte pRoxy representations (ORDER), a probabilistic framework which leverages novel state representations to improve the robustness against diverse masked observabilities. Specifically, we propose a discrete representation of the states and use a proxy representation to recover the states from masked partial observable trajectories. The training of ORDER can be compactly described as the following three steps. i) Learning the discrete state representations on data with full observations, ii) Training the decision module based on the discrete representations, and iii) Training the proxy discrete representations on the data with various partial observations, aligning with the discrete representations. We conduct extensive experiments to evaluate ORDER, showcasing its effectiveness in offline RL for diverse partially observable scenarios and highlighting the significance of discrete proxy representations in generalization performance. ORDER is a flexible framework to employ any offline RL algorithms and we hope that ORDER can pave the way for the deployment of RL policy against various partial observabilities in the real world.