An Information-theoretic Analysis Of OOD Generalization In Meta-reinforcement Learning

Abstract

In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalization bounds for meta-supervised learning under two distinct distribution shift scenarios: standard distribution mismatch and a broad-to-narrow training setting. Building on this foundation, we formalize the generalization problem in meta-reinforcement learning and establish fine-grained generalization bounds that exploit the structure of Markov Decision Processes. Lastly, we analyze the generalization performance of a gradient-based meta-reinforcement learning algorithm.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2025an

Related papers

• Rethinking Out-of-distribution Detection For Reinforcement Learning: Advancing Methods For Evaluation And Detection (2024)2.26
• Theoretical Analysis Of Meta Reinforcement Learning: Generalization Bounds And Convergence Guarantees (2024)10.35
• The Role Of Pretrained Representations For The OOD Generalization Of Reinforcement Learning Agents (2021)0.00
• Galilai: Out-of-task Distribution Detection Using Causal Active Experimentation For Safe Transfer RL (2021)0.00
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• Out-of-distribution Dynamics Detection: Rl-relevant Benchmarks And Results (2021)0.00
• Goal Misgeneralization In Deep Reinforcement Learning (2021)0.00
• Improving Generalization In Meta Reinforcement Learning Using Learned Objectives (2019)0.00