MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning

TL;DR

MDP Playground is a versatile testbed for RL agents that allows controlled manipulation of environment difficulty across various dimensions, aiding in understanding, debugging, and improving reinforcement learning algorithms in both toy and complex settings.

Contribution

Introduces a flexible, parameterized RL testbed with controllable environment dimensions, enabling systematic analysis and debugging of RL agents across toy and real-world environments.

Findings

Controlled environment dimensions reveal their impact on agent performance.

Wrappers effectively inject dimensions into existing environments.

Insights gained help improve RL agent robustness and understanding.

Abstract

We present MDP Playground, a testbed for Reinforcement Learning (RL) agents with dimensions of hardness that can be controlled independently to challenge agents in different ways and obtain varying degrees of hardness in toy and complex RL environments. We consider and allow control over a wide variety of dimensions, including delayed rewards, sequence lengths, reward density, stochasticity, image representations, irrelevant features, time unit, action range and more. We define a parameterised collection of fast-to-run toy environments in OpenAI Gym by varying these dimensions and propose to use these to understand agents better. We then show how to design experiments using MDP Playground to gain insights on the toy environments. We also provide wrappers that can inject many of these dimensions into any Gym environment. We experiment with these wrappers on Atari and Mujoco to allow for understanding the effects of these dimensions on environments that are more complex than the toy environments. We also compare the effect of the dimensions on the toy and complex environments. Finally, we show how to use MDP Playground to debug agents, to study the interaction of multiple dimensions and describe further use-cases.