Atari Games On Atari 2600 Seaquest

Score

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
GDI-H3	1000000	Generalized Data Distribution Iteration	-
GDI-H3(200M frames)	1000000	Generalized Data Distribution Iteration	-
Agent57	999997.63	Agent57: Outperforming the Atari Human Benchmark
R2D2	999996.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero	999976.52	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)	999659.18	Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-I3	943910	Generalized Data Distribution Iteration	-
GDI-I3	943910	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Ape-X	392952.3	Distributed Prioritized Experience Replay
C51 noop	266434.0	A Distributional Perspective on Reinforcement Learning
Duel noop	50254.2	Dueling Network Architectures for Deep Reinforcement Learning
Duel hs	37361.6	Dueling Network Architectures for Deep Reinforcement Learning
IQN	30140	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	29278.6	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior noop	26357.8	Prioritized Experience Replay
Prior hs	25463.7	Prioritized Experience Replay
NoisyNet-Dueling	16754	Noisy Networks for Exploration
DDQN (tuned) noop	16452.7	Dueling Network Architectures for Deep Reinforcement Learning
DDQN (tuned) hs	14498.0	Deep Reinforcement Learning with Double Q-learning
Persistent AL	13230.74	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 57 row(s) selected.