Atari Games On Atari 2600 Beam Rider

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 LSTM hs	24622.2	Asynchronous Methods for Deep Reinforcement Learning
Prior noop	23384.2	Prioritized Experience Replay
IMPALA (deep)	32463.47	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DQN hs	9743.2	Deep Reinforcement Learning with Double Q-learning
DDQN+Pop-Art noop	8299.4	Learning values across many orders of magnitude	-
Duel noop	12164.0	Dueling Network Architectures for Deep Reinforcement Learning
Nature DQN	6846.0	Human level control through deep reinforcement learning
POP3D	4549	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Best Learner	929.4	The Arcade Learning Environment: An Evaluation Platform for General Agents
DQN Best	5184	Playing Atari with Deep Reinforcement Learning
SARSA	1743.0	-	-
DreamerV2	18646	Mastering Atari with Discrete World Models
Gorila	3822.1	Massively Parallel Methods for Deep Reinforcement Learning
RIMs-PPO	5320	Recurrent Independent Mechanisms
Prior+Duel noop	30276.5	Dueling Network Architectures for Deep Reinforcement Learning
A3C FF (1 day) hs	13235.9	Asynchronous Methods for Deep Reinforcement Learning
CGP	1341.6	Evolving simple programs for playing Atari games
UCT	6624.6	The Arcade Learning Environment: An Evaluation Platform for General Agents
IQ-Learn	-	IQ-Learn: Inverse soft-Q Learning for Imitation
MuZero (Res2 Adam)	333077.44	Online and Offline Reinforcement Learning by Planning with a Learned Model

0 of 49 row(s) selected.