Atari Games On Atari 2600 Tutankham

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	2354.91	Agent57: Outperforming the Atari Human Benchmark
MuZero	491.48	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3	423.9	Generalized Data Distribution Iteration	-
GDI-I3	423.9	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-H3	418.2	Generalized Data Distribution Iteration	-
R2D2	395.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero (Res2 Adam)	347.99	Online and Offline Reinforcement Learning by Planning with a Learned Model
A2C + SIL	340.5	Self-Imitation Learning
QR-DQN-1	297	Distributional Reinforcement Learning with Quantile Regression
IQN	293	Implicit Quantile Networks for Distributional Reinforcement Learning
IMPALA (deep)	292.11	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
C51 noop	280.0	A Distributional Perspective on Reinforcement Learning
Ape-X	272.6	Distributed Prioritized Experience Replay
NoisyNet-Dueling	269	Noisy Networks for Exploration
DreamerV2	264	Mastering Atari with Discrete World Models
ASL DDQN	252.9	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop	245.9	Dueling Network Architectures for Deep Reinforcement Learning
Advantage Learning	245.22	Increasing the Action Gap: New Operators for Reinforcement Learning
POP3D	241.21	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
UCT	225.5	The Arcade Learning Environment: An Evaluation Platform for General Agents

0 of 44 row(s) selected.