S-RL Toolbox: Environments, Datasets And Evaluation Metrics For State Representation Learning

Abstract

State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. However, the diversity in applications and methods makes the field lack standard evaluation datasets, metrics and tasks. This paper provides a set of environments, data generators, robotic control tasks, metrics and tools to facilitate iterative state representation learning and evaluation in reinforcement learning settings.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyraffin2018s

Related papers

• State Representation Learning For Control: An Overview (2018)17.39
• A Survey Of State Representation Learning For Deep Reinforcement Learning (2025)0.00
• Toybox: A Suite Of Environments For Experimental Evaluation Of Deep Reinforcement Learning (2019)0.00
• Unsupervised Representation Learning In Deep Reinforcement Learning: A Review (2022)9.59
• Discovering Minimal Reinforcement Learning Environments (2024)0.00
• Bootstrapped Representations In Reinforcement Learning (2023)0.00
• Learning To Identify Critical States For Reinforcement Learning From Videos (2023)8.76
• Rl_reach: Reproducible Reinforcement Learning Experiments For Robotic Reaching Tasks (2021)5.84