Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field

2019-08-13 · Marin Toromanoff, Emilie Wirbel, Fabien Moutarde

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.

📄 PDF Abstract BibTeX arXiv:1908.04683

Code (1)

valeoai/rainbow-iqn-apex 공식 구현 pytorch

Tasks

Atari GamesDeep Reinforcement LearningGeneral Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

On Multi-Agent Learning in Team Sports Games

2019-06-25 · Yunqi Zhao, Igor Borovikov, Jason Rupert, Caedmon Somers 외

In recent years, reinforcement learning has been successful in solving video games from Atari to Star Craft II. However, the end-to-end model-free reinforcement learning (RL) is not sample efficient and requires a signif…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions

2021-12-08 · Jiajun Fan

The Arcade Learning Environment (ALE) is proposed as an evaluation platform for empirically assessing the generality of agents across dozens of Atari 2600 games. ALE offers various challenging problems and has drawn sign…

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions

2021-11-24 · AAAI Workshop ML4OR-22 2022 2 · Anonymous

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

An Elementary Proof that Q-learning Converges Almost Surely

2021-08-05 · Matthew T. Regehr, Alex Ayoub

Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [W…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adversarial Policies Beat Superhuman Go AIs

2022-11-01 · Tony T. Wang, Adam Gleave, Tom Tseng, Kellin Pelrine 외

We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our adversaries do not win by playing Go we…