paper-with-me

홈 › Papers

Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning

2025-07-24 · Leiji Zhang, Zeyu Wang, Xin Li, Yao-Hui Li arxiv

Bisimulation metric has long been regarded as an effective control-related representation learning technique in various reinforcement learning tasks. However, in this paper, we identify two main issues with the conventional bisimulation metric: 1) an inability to represent certain distinctive scenarios, and 2) a reliance on predefined weights for differences in rewards and subsequent states during recursive updates. We find that the first issue arises from an imprecise definition of the reward gap, whereas the second issue stems from overlooking the varying importance of reward difference and next-state distinctions across different training stages and task settings. To address these issues, by introducing a measure for state-action pairs, we propose a revised bisimulation metric that features a more precise definition of reward gap and novel update operators with adaptive coefficient. We also offer theoretical guarantees of convergence for our proposed metric and its improved representation distinctiveness. In addition to our rigorous theoretical analysis, we conduct extensive experiments on two representative benchmarks, DeepMind Control and Meta-World, demonstrating the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2507.18519

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningReinforcement Learning

Similar Papers 제목 키워드 기반

Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation

2022-01-28 · Martin Bertran, Walter Talbott, Nitish Srivastava, Joshua Susskind

Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning. Recently, there has been renewed interest in bisimulation metrics as a tool to…

Data AugmentationReinforcement Learning (RL)Semantic SimilaritySemantic Textual Similarity

Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions

2023-02-12 · Qiyuan Liu, Qi Zhou, Rui Yang, Jie Wang

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to …

ClusteringReinforcement Learning (RL)Representation Learning

Invariant Representations for Reinforcement Learning without Reconstruction

2021-01-01 · ICLR 2021 1 · Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal 외

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations …

Causal InferenceMuJoCoreinforcement-learningReinforcement Learning+2

Learning Invariant Representations for Reinforcement Learning without Reconstruction

2020-06-18 · Amy Zhang, Rowan McAllister, Roberto Calandra, Yarin Gal 외

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations …

Causal InferenceMuJoCoreinforcement-learningReinforcement Learning+2

Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning

2023-09-21 · NeurIPS 2023 11

While bisimulation-based approaches hold promise for learning robust state representations for Reinforcement Learning (RL) tasks, their efficacy in offline RL tasks has not been up to par. In some instances, their perfo…