Atari Games On Atari 2600 Zaxxon

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

模型名称	Score	Paper Title	Repository
Best Learner	3365.1	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
DQN hs	4412.0	Deep Reinforcement Learning with Double Q-learning	-
DreamerV2	50699	Mastering Atari with Discrete World Models	-
NoisyNet-Dueling	14874	Noisy Networks for Exploration	-
IQN	21772	Implicit Quantile Networks for Distributional Reinforcement Learning	-
RIMs-PPO	15000	Recurrent Independent Mechanisms	-
DDQN+Pop-Art noop	14402.0	Learning values across many orders of magnitude	-
DNA	22588	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
QR-DQN-1	13112	Distributional Reinforcement Learning with Quantile Regression	-
Prior+Duel noop	13886.0	Dueling Network Architectures for Deep Reinforcement Learning	-
Agent57	249808.9	Agent57: Outperforming the Atari Human Benchmark	-
GDI-H3	216020	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	154131.86	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
GDI-I3	109140	Generalized Data Distribution Iteration	-
IMPALA (deep)	32935.50	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
Gorila	6159.4	Massively Parallel Methods for Deep Reinforcement Learning	-
Prior hs	9474.0	Prioritized Experience Replay	-
A3C FF (1 day) hs	2659.0	Asynchronous Methods for Deep Reinforcement Learning	-
POP3D	9472	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
Advantage Learning	9129.61	Increasing the Action Gap: New Operators for Reinforcement Learning	-

0 of 41 row(s) selected.