Atari Games On Atari 2600 Ms Pacman

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
A3C FF hs	653.7	Asynchronous Methods for Deep Reinforcement Learning	-
CGP	2568	Evolving simple programs for playing Atari games	-
SARSA	1227.0	-	-
Nature DQN	2311.0	Human level control through deep reinforcement learning
GDI-I3	11536	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Best Learner	1691.8	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
CURL	1492.8	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	-
NoisyNet-Dueling	5546	Noisy Networks for Exploration	-
MFEC	8530.4004	Model-Free Episodic Control with State Aggregation	-
FQF	7631.9	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	-
POP3D	1683.87	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
MuZero (Res2 Adam)	70659.76	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
Ape-X	11255.2	Distributed Prioritized Experience Replay	-
DQN noop	3085.6	Deep Reinforcement Learning with Double Q-learning	-
A2C + SIL	4025.1	Self-Imitation Learning	-
UCT	22336	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
Prior+Duel noop	3327.3	Dueling Network Architectures for Deep Reinforcement Learning	-
DDQN (tuned) hs	1241.3	Deep Reinforcement Learning with Double Q-learning	-
QR-DQN-1	5821	Distributional Reinforcement Learning with Quantile Regression	-
DDQN (tuned) noop	2711.4	Dueling Network Architectures for Deep Reinforcement Learning	-

0 of 47 row(s) selected.