paper-with-me

홈 › Papers

Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection

2023-05-09 · Jiajun Fan, Yuzheng Zhuang, Yuecheng Liu, Jianye Hao, Bin Wang, Jiangcheng Zhu, Hao Wang, Shu-Tao Xia

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 collect samples with diverse behaviors derived from a population of different exploratory policies. Adaptive policy selection has been adopted for behavior control. However, the behavior selection space is largely limited by the predefined policy population, which further limits behavior diversity. In this paper, we propose a general framework called Learnable Behavioral Control (LBC) to address the limitation, which a) enables a significantly enlarged behavior selection space via formulating a hybrid behavior mapping from all policies; b) constructs a unified learnable process for behavior selection. We introduce LBC into distributed off-policy actor-critic methods and achieve behavior control via optimizing the selection of the behavior mappings with bandit-based meta-controllers. Our agents have achieved 10077.52% mean human normalized score and surpassed 24 human world records within 1B training frames in the Arcade Learning Environment, which demonstrates our significant state-of-the-art (SOTA) performance without degrading the sample efficiency.

📄 PDF Abstract BibTeX arXiv:2305.05239

Code (0)

등록된 구현이 없습니다.

Tasks

Atari GamesDeep Reinforcement LearningDiversityReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

2022-03-31 · Yang Shao, Quan Kong, Tadayuki Matsumura, Taiki Fuji 외

We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achieve a simulation environment for the POMD…

Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1

Estimating Central, Peripheral, and Temporal Visual Contributions to Human Decision Making in Atari Games

2026-04-06 · Henrik Krauss, Takehisa Yairi arxiv

We study how different visual information sources contribute to human decision making in dynamic visual environments. Using Atari-HEAD, a large-scale Atari gameplay dataset with synchronized eye-tracking, we introduce a …

Decision MakingAtari Games

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning

2024-06-06 · Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Kristian Kersting

Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggl…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Evolving simple programs for playing Atari games

2018-06-14 · Dennis G Wilson, Sylvain Cussat-Blanc, Hervé Luga, Julian F. Miller

Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing…

Atari Games

Mastering Atari with Discrete World Models

2020-10-05 · ICLR 2021 1 · Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba

Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-effi…

Atari GamesGPU