Atari Games On Atari 2600 Private Eye

评估指标

Score

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Go-Explore	95756	First return, then explore
Agent57	79716.46	Agent57: Outperforming the Atari Human Benchmark
SND-VIC	17313	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
MuZero	15299.98	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3	15100	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-H3	15100	Generalized Data Distribution Iteration	-
GDI-I3	15100	Generalized Data Distribution Iteration	-
C51 noop	15095.0	A Distributional Perspective on Reinforcement Learning
SND-STD	15089	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
CGP	12702.2	Evolving simple programs for playing Atari games
RND	8666	Exploration by Random Network Distillation
DQN-PixelCNN	8358.7	Count-Based Exploration with Neural Density Models
R2D2	5322.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Advantage Learning	5276.16	Increasing the Action Gap: New Operators for Reinforcement Learning
SND-V	4213	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
Intrinsic Reward Agent	3036.5	Large-Scale Study of Curiosity-Driven Learning
Gorila	2598.6	Massively Parallel Methods for Deep Reinforcement Learning
DreamerV2	2198	Mastering Atari with Discrete World Models
Best Baseline	1947.3	The Arcade Learning Environment: An Evaluation Platform for General Agents
Bootstrapped DQN	1812.5	Deep Exploration via Bootstrapped DQN

0 of 52 row(s) selected.