Mastering Atari Games with Limited Data

Authors: Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, Yang Gao

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method achieves 190.4% mean human performance and 116.0% median performance on the Atari 100k benchmark with only two hours of real-time game experience and outperforms the state SAC in some tasks on the DMControl 100k benchmark.
Researcher Affiliation Academia Weirui Ye Shaohuai Liu Thanard Kurutach Pieter Abbeel Yang Gao Tsinghua University, UC Berkeley, Shanghai Qi Zhi Institute {ywr20, liush20}@mails.tsinghua.edu.cn, gaoyangiiis@tsinghua.edu.cn {thanard.kurutach, pabbeel}@berkeley.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes We implement our algorithm in an easy-to-understand manner and it is available at https://github.com/Ye WR/Efficient Zero.
Open Datasets Yes More specifically, we use the Atari 100k benchmark. Intuitively, this benchmark asks the agent to learn to play Atari games within two hours of real-world game time.
Dataset Splits Yes We split this dataset into a training set and a validation set.
Hardware Specification No The paper does not provide specific details regarding the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for ancillary software dependencies used in the experiments.
Experiment Setup Yes The benchmark allows the agent to interact with 100 thousand environment steps, i.e. 400 thousand frames due to a frameskip of 4, with each environment.