Towards Robust Bisimulation Metric Learning
2021 · Mete Kemertas, Tristan Aumentado-Armstrong
Abstract
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich representations, often learned via modern function approximation techniques, can enable practical application of the policy improvement theorem, even in high-dimensional continuous state-action spaces. Bisimulation metrics offer one solution to this representation learning problem, by collapsing functionally similar states together in representation space, which promotes invariance to noise and distractors. In this work, we generalize value function approximation bounds for on-policy bisimulation metrics to non-optimal policies and approximate environment dynamics. Our theoretical results help us identify embedding pathologies that may occur in practical use. In particular, we find that these issues stem from an underconstrained dynamics model and an unstable
Authors
(none)
Tags
Stats
Related papers
- Understanding Behavioral Metric Learning: A Large-scale Study On Distracting Reinforcement Learning Environments (2025)0.00
- Understanding And Addressing The Pitfalls Of Bisimulation-based Representations In Offline Reinforcement Learning (2023)1.40
- Generalization Across Observation Shifts In Reinforcement Learning (2023)0.00
- Simsr: Simple Distance-based State Representation For Deep Reinforcement Learning (2021)0.00
- Stable Offline Value Function Learning With Bisimulation-based Representations (2024)0.00
- Provable Performance Bounds For Digital Twin-driven Deep Reinforcement Learning In Wireless Networks: A Novel Digital-twin Bisimulation Metric (2025)0.00
- Simplifying Model-based RL: Learning Representations, Latent-space Models, And Policies With One Objective (2022)0.00
- Low-dimensional State And Action Representation Learning With MDP Homomorphism Metrics (2021)0.00