Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
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.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Kaleigh Clary (edit)
Emma Tosch (edit)
John Foley (edit)
David Jensen (edit)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
Stargazers:
3
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
3
Language:
R
Code for experiments in Let’s Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
04/14/19 06:01PM
2,827
1,070
Tweets
arxivml: "Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments", Kaleigh Clary, Emma To… https://t.co/jgxvEScadh
arxiv_cs_LG: Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments. Kaleigh Clary, Emma Tosch, John Foley, and David Jensen https://t.co/dLP9V6KlZs
BrundageBot: Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments. Kaleigh Clary, Emma Tosch, John Foley, and David Jensen https://t.co/8PMTEcw6x3
Images
Related