Learnable behavior control: Breaking atari human world records via sample-efficient behavior selection

J Fan, Y Zhuang, Y Liu, J Hao, B Wang, J Zhu… - arxiv preprint arxiv …, 2023 - arxiv.org
The exploration problem is one of the main challenges in deep reinforcement learning (RL).
Recent promising works tried to handle the problem with population-based methods, which …

A review for deep reinforcement learning in atari: Benchmarks, challenges, and solutions

J Fan - arxiv preprint arxiv:2112.04145, 2021 - arxiv.org
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 …

Generalized data distribution iteration

J Fan, C **ao - arxiv preprint arxiv:2206.03192, 2022 - arxiv.org
To obtain higher sample efficiency and superior final performance simultaneously has been
one of the major challenges for deep reinforcement learning (DRL). Previous work could …