Simsr: Simple Distance-based State Representation For Deep Reinforcement Learning

Abstract

This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods. Addressing the computational complexity, stringent assumptions and representation collapse challenges in existing work of bisimulation metric, we devise Simple State Representation (SimSR) operator. SimSR enables us to design a stochastic approximation method that can practically learn the mapping functions (encoders) from observations to latent representation space. In addition to the theoretical analysis and comparison with the existing work, we experimented and compared our work with recent state-of-the-art solutions in visual MuJoCo tasks. The results shows that our model generally achieves better performance and has better robustness and good generalization.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzang2021simsr

Related papers

• Towards Robust Bisimulation Metric Learning (2021)0.00
• Mico: Improved Representations Via Sampling-based State Similarity For Markov Decision Processes (2021)0.00
• A Survey Of State Representation Learning For Deep Reinforcement Learning (2025)0.00
• State Chrono Representation For Enhancing Generalization In Reinforcement Learning (2024)0.00
• State Representation Learning For Control: An Overview (2018)17.39
• Low-dimensional State And Action Representation Learning With MDP Homomorphism Metrics (2021)0.00
• Value-consistent Representation Learning For Data-efficient Reinforcement Learning (2022)0.00
• Bootstrapped Representations In Reinforcement Learning (2023)0.00