ToyBox: Better Atari Environments for Testing Reinforcement Learning Agents

Abstract

It is a widely accepted principle that software without tests has bugs. Testing reinforcement learning agents is especially difficult because of the stochastic nature of both agents and environments, the complexity of state-of-the-art models, and the sequential nature of their predictions. Recently, the Arcade Learning Environment (ALE) has become one of the most widely used benchmark suites for deep learning research, and state-of-the-art Reinforcement Learning (RL) agents have been shown to routinely equal or exceed human performance on many ALE tasks. Since ALE is based on emulation of original Atari games, the environment does not provide semantically meaningful representations of internal game state. This means that ALE has limited utility as an environment for supporting testing or model introspection. We propose ToyBox, a collection of reimplementations of these games that solves this critical problem and enables robust testing of RL agents.

NeurIPS Systems for ML Workshop

References in corpus (7)

• Playing Atari with Deep Reinforcement Learning
• StarCraft II: A New Challenge for Reinforcement Learning
• TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
• Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
• Distributed Evaluations: Ending Neural Point Metrics
• Terrain RL Simulator
• Game AI Research with Fast Planet Wars Variants

Cited by in corpus (3)

• Learning with AMIGo: Adversarially Motivated Intrinsic Goals
• RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments
• Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning