Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning

By Emma Tosch, Kaleigh Clary, John Foley, David D. Jensen. 2019

9 citations recorded by the source corpus.

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. *this https URL

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Akanksha Atrey
2. Kaleigh Clary
3. David D. Jensen

Citations in the corpus

• Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning (2019, methodology): “T OY B OX was developed to support experimental evaluation and behavioral tests of deep RL models (Tosch et al., 2019”