Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

04/12/2019
by   Kaleigh Clary, et al.
0

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment. Unfortunately, there are still pernicious sources of variability in reinforcement learning agents that make reporting common summary statistics an unsound metric for performance. Our experiments demonstrate the variability of common agents used in the popular OpenAI Baselines repository. We make the case for reporting post-training agent performance as a distribution, rather than a point estimate.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset