Toybox: A Suite Of Environments For Experimental Evaluation Of Deep Reinforcement Learning

Abstract

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted to producing high quality environments for experimental evaluation of agent behavior. We present TOYBOX, a new high-performance, open-source* subset of Atari environments re-designed for the experimental evaluation of deep RL. We show that TOYBOX enables a wide range of experiments and analyses that are impossible in other environments. *https://kdl-umass.github.io/Toybox/

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytosch2019toybox

Related papers

• Toybox: Better Atari Environments For Testing Reinforcement Learning Agents (2018)0.00
• Discovering Minimal Reinforcement Learning Environments (2024)0.00
• Eden: A Unified Environment Framework For Booming Reinforcement Learning Algorithms (2021)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Rl_reach: Reproducible Reinforcement Learning Experiments For Robotic Reaching Tasks (2021)5.84
• Is Deep Reinforcement Learning Really Superhuman On Atari? Leveling The Playing Field (2019)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• Jumanji: A Diverse Suite Of Scalable Reinforcement Learning Environments In JAX (2023)0.00