Atari Games On Atari 2600 Star Gunner

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	839573.53	Agent57: Outperforming the Atari Human Benchmark
R2D2	717344.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
GDI-H3	677590	Generalized Data Distribution Iteration	-
MuZero	549271.70	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3	465750	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	465750	Generalized Data Distribution Iteration	-
Ape-X	434342.5	Distributed Prioritized Experience Replay
IMPALA (deep)	200625.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
A3C LSTM hs	164766.0	Asynchronous Methods for Deep Reinforcement Learning
MuZero (Res2 Adam)	154548.26	Online and Offline Reinforcement Learning by Planning with a Learned Model
A3C FF hs	138218.0	Asynchronous Methods for Deep Reinforcement Learning
FQF	131981.2	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
ASL DDQN	129140	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel hs	127073.0	Deep Reinforcement Learning with Double Q-learning
Prior+Duel noop	125117.0	Dueling Network Architectures for Deep Reinforcement Learning
DNA	104125	DNA: Proximal Policy Optimization with a Dual Network Architecture
Duel hs	90804.0	Dueling Network Architectures for Deep Reinforcement Learning
Duel noop	89238.0	Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-1	77495	Distributional Reinforcement Learning with Quantile Regression
NoisyNet-Dueling	75867	Noisy Networks for Exploration

0 of 43 row(s) selected.