A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions

Abstract

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 significant attention from the deep reinforcement learning (RL) community. From Deep Q-Networks (DQN) to Agent57, RL agents seem to achieve superhuman performance in ALE. However, is this the case? In this paper, to explore this problem, we first review the current evaluation metrics in the Atari benchmarks and then reveal that the current evaluation criteria of achieving superhuman performance are inappropriate, which underestimated the human performance relative to what is possible. To handle those problems and promote the development of RL research, we propose a novel Atari benchmark based on human world records (HWR), which puts forward higher requirements for RL agents on both final performance and learning efficiency. Furthermore, we summarize the state-of-the-art (SO

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfan2021a

Related papers

• Is Deep Reinforcement Learning Really Superhuman On Atari? Leveling The Playing Field (2019)0.00
• Revisiting The Arcade Learning Environment: Evaluation Protocols And Open Problems For General Agents (2017)15.67
• Importance Of Using Appropriate Baselines For Evaluation Of Data-efficiency In Deep Reinforcement Learning For Atari (2020)0.00
• Deep Reinforcement Learning At The Edge Of The Statistical Precipice (2021)0.00
• Toybox: Better Atari Environments For Testing Reinforcement Learning Agents (2018)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• Reward Learning From Human Preferences And Demonstrations In Atari (2018)0.00