Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning
arXiv:1905.02825
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/
References in corpus (7)
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Massively Parallel Methods for Deep Reinforcement Learning
- Hybrid Reward Architecture for Reinforcement Learning
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
- Modularization of End-to-End Learning: Case Study in Arcade Games
- Fast Reinforcement Learning with Large Action Sets using Error-Correcting Output Codes for MDP Factorization