Atari Games On Atari 2600 Hero

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
Agent57	114736.26	Agent57: Outperforming the Atari Human Benchmark
MuZero	49244.11	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2	39537.1	Recurrent Experience Replay in Distributed Reinforcement Learning	-
C51 noop	38874	A Distributional Perspective on Reinforcement Learning
GDI-I3	38330	Generalized Data Distribution Iteration	-
GDI-I3	38330	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-H3	38225	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	37234.31	Online and Offline Reinforcement Learning by Planning with a Learned Model
IMPALA (deep)	33730.55	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
A2C + SIL	33156.7	Self-Imitation Learning
A3C FF hs	32464.1	Asynchronous Methods for Deep Reinforcement Learning
Ape-X	31655.9	Distributed Prioritized Experience Replay
NoisyNet-Dueling	31533	Noisy Networks for Exploration
FQF	30926.2	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
A3C LSTM hs	28889.5	Asynchronous Methods for Deep Reinforcement Learning
A3C FF (1 day) hs	28765.8	Asynchronous Methods for Deep Reinforcement Learning
IQN	28386	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	26578.5	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DNA	24904	DNA: Proximal Policy Optimization with a Dual Network Architecture
Advantage Learning	24788.86	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 44 row(s) selected.