Atari Games On Atari 2600 Wizard Of Wor

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
Prior noop	4802.0	Prioritized Experience Replay
A2C + SIL	7088.3	Self-Imitation Learning
Prior hs	5727.0	Prioritized Experience Replay
R2D2	144362.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero (Res2 Adam)	100096.6	Online and Offline Reinforcement Learning by Planning with a Learned Model
DreamerV2	12851	Mastering Atari with Discrete World Models
ES FF (1 hour) noop	3480.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Best Learner	1981.3	The Arcade Learning Environment: An Evaluation Platform for General Agents
DDQN+Pop-Art noop	483.0	Learning values across many orders of magnitude	-
GDI-H3	63735	Generalized Data Distribution Iteration	-
Gorila	10431.0	Massively Parallel Methods for Deep Reinforcement Learning
DQN noop	2704.0	Deep Reinforcement Learning with Double Q-learning
Ape-X	46204	Distributed Prioritized Experience Replay
GDI-I3	64239	Generalized Data Distribution Iteration	-
Agent57	157306.41	Agent57: Outperforming the Atari Human Benchmark
Prior+Duel noop	12352.0	Dueling Network Architectures for Deep Reinforcement Learning
UCT	105500	The Arcade Learning Environment: An Evaluation Platform for General Agents
NoisyNet-Dueling	9149	Noisy Networks for Exploration
Nature DQN	3393.0	Human level control through deep reinforcement learning
DDQN (tuned) hs	6201.0	Deep Reinforcement Learning with Double Q-learning

0 of 41 row(s) selected.