Atari Games On Atari 2600 Wizard Of Wor

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
MuZero	197126.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	157306.41	Agent57: Outperforming the Atari Human Benchmark
R2D2	144362.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
UCT	105500	The Arcade Learning Environment: An Evaluation Platform for General Agents
MuZero (Res2 Adam)	100096.6	Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-I3	64239	Generalized Data Distribution Iteration	-
GDI-H3	63735	Generalized Data Distribution Iteration	-
Ape-X	46204	Distributed Prioritized Experience Replay
FQF	44782.6	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
IQN	31190	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	25061	Distributional Reinforcement Learning with Quantile Regression
ASL DDQN	21049	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DNA	20851	DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C LSTM hs	18082.0	Asynchronous Methods for Deep Reinforcement Learning
A3C FF hs	17244.0	Asynchronous Methods for Deep Reinforcement Learning
DreamerV2	12851	Mastering Atari with Discrete World Models
Prior+Duel noop	12352.0	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs	10471.0	Deep Reinforcement Learning with Double Q-learning
Gorila	10431.0	Massively Parallel Methods for Deep Reinforcement Learning
Advantage Learning	9541.14	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 41 row(s) selected.