Information-Theoretic Generalization Bounds for Batch Reinforcement Learning
We analyze the generalization properties of batch reinforcement learning (batch RL) with value function approximation from an information-theoretic perspective. We derive generalization bounds for batch RL using (conditional) mutual information. In addition, we demonstrate how to establish a connect...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/26/11/995 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | We analyze the generalization properties of batch reinforcement learning (batch RL) with value function approximation from an information-theoretic perspective. We derive generalization bounds for batch RL using (conditional) mutual information. In addition, we demonstrate how to establish a connection between certain structural assumptions on the value function space and conditional mutual information. As a by-product, we derive a <i>high-probability</i> generalization bound via conditional mutual information, which was left open and may be of independent interest. |
|---|---|
| ISSN: | 1099-4300 |