Atari Games On Atari 2600 Frostbite

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	631378.53	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	541280.88	Agent57: Outperforming the Atari Human Benchmark
MuZero (Res2 Adam)	374769.76	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	315456.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Fearlessmrx	214060	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DreamerV2	11384	Mastering Atari with Discrete World Models
GDI-H3(200M frames)	11330	Generalized Data Distribution Iteration	-
GDI-H3	11330	Generalized Data Distribution Iteration	-
GDI-I3	10485	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	10485	Generalized Data Distribution Iteration	-
Ape-X	9328.6	Distributed Prioritized Experience Replay
ASL DDQN	8616.4	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop	7413.0	Dueling Network Architectures for Deep Reinforcement Learning
A2C + SIL	6289.8	Self-Imitation Learning
TRPO-hash	5214.0	#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Duel noop	4672.8	Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-1	4384	Distributional Reinforcement Learning with Quantile Regression
Prior noop	4380.1	Prioritized Experience Replay
IQN	4324	Implicit Quantile Networks for Distributional Reinforcement Learning
Prior+Duel hs	4038.4	Deep Reinforcement Learning with Double Q-learning

0 of 53 row(s) selected.