Atari Games On Atari 2600 Centipede

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	1422628	First return, then explore
GDI-H3(1B frames)	1359533	GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning	-
MuZero	1159049.27	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)	874301.64	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	599140.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	412847.86	Agent57: Outperforming the Atari Human Benchmark
GDI-H3	195630	Generalized Data Distribution Iteration	-
GDI-I3	155830	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	155830	Generalized Data Distribution Iteration	-
Full Tree	125123	The Arcade Learning Environment: An Evaluation Platform for General Agents
DNA	100194	DNA: Proximal Policy Optimization with a Dual Network Architecture
DDQN+Pop-Art noop	49065.8	Learning values across many orders of magnitude	-
CGP	24708	Evolving simple programs for playing Atari games
Ape-X	12974	Distributed Prioritized Experience Replay
QR-DQN-1	12447	Distributional Reinforcement Learning with Quantile Regression
DreamerV2	11883	Mastering Atari with Discrete World Models
IQN	11561	Implicit Quantile Networks for Distributional Reinforcement Learning
IMPALA (deep)	11049.75	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
C51 noop	9646.0	A Distributional Perspective on Reinforcement Learning
Best Learner	8803.8	The Arcade Learning Environment: An Evaluation Platform for General Agents

0 of 45 row(s) selected.