REVIEW 3 cited by
Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can lead to very different performance. In this work, we discuss the difficulties of comparing different agents trained on ALE. In order to take a step further towards reproducible and comparable DRL, we introduce SABER, a Standardized Atari BEnchmark for general Reinforcement learning algorithms. Our methodology extends previous recommendations and contains a complete set of environment parameters as well as train and test procedures. We then use SABER to evaluate the current state of the art, Rainbow. Furthermore, we introduce a human world records baseline, and argue that previous claims of expert or superhuman performance of DRL might not be accurate. Finally, we propose Rainbow-IQN by extending Rainbow with Implicit Quantile Networks (IQN) leading to new state-of-the-art performance. Source code is available for reproducibility.
Forward citations
Cited by 3 Pith papers
-
Playstyle and Artificial Intelligence: An Initial Blueprint Through the Lens of Video Games
This dissertation formalizes playstyle as the decision-making style of an agent, introduces a discrete-state playstyle distance that distinguishes behaviors in racing games and Atari, and proposes a blueprint for usin...
-
Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi
Agents trained with an action space augmented by human Hanabi conventions learn faster and score higher than baseline Rainbow agents, and they cooperate better with unfamiliar partners.
-
Decorrelated Soft Actor-Critic for Efficient Deep Reinforcement Learning
Decorrelated Soft Actor-Critic (DSAC) adds layerwise input decorrelation to discrete SAC and reports faster wall-clock training in 5 of 7 Atari games and better reward in 2, though the gains are partly confounded by p...
Discussion (0). Continue with ORCID to comment.