HyperAI超神经

首页算力平台文档资讯论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Atari Games On Atari Game

评估指标

Human World Record Breakthrough

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
GDI-H3	22	Generalized Data Distribution Iteration	-
Muzero	19	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	18	Agent57: Outperforming the Atari Human Benchmark
Go-Explore	17	Go-Explore: a New Approach for Hard-Exploration Problems
GDI-I3	17	Generalized Data Distribution Iteration	-
R2D2	15	Recurrent Experience Replay in Distributed Reinforcement Learning	-
NGU	8	Never Give Up: Learning Directed Exploration Strategies
Muesli	5	Muesli: Combining Improvements in Policy Optimization
Rainbow	4	Rainbow: Combining Improvements in Deep Reinforcement Learning

0 of 9 row(s) selected.

Atari Games On Atari Game | SOTA | HyperAI超神经