Atari Games On Atari 2600 Video Pinball

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
R2D2	999383.2	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	992340.74	Agent57: Outperforming the Atari Human Benchmark
MuZero	981791.88	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-H3	978190	Generalized Data Distribution Iteration	-
C51 noop	949604.0	A Distributional Perspective on Reinforcement Learning
GDI-I3	925830	Generalized Data Distribution Iteration	-
NoisyNet-Dueling	870954	Noisy Networks for Exploration
MuZero (Res2 Adam)	865543.44	Online and Offline Reinforcement Learning by Planning with a Learned Model
Bootstrapped DQN	811610	Deep Exploration via Bootstrapped DQN
QR-DQN-1	705662	Distributional Reinforcement Learning with Quantile Regression
IQN	698045	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	626794	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
IMPALA (deep)	572898.27	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Ape-X	565163.2	Distributed Prioritized Experience Replay
Advantage Learning	543504	Increasing the Action Gap: New Operators for Reinforcement Learning
DNA	505392	DNA: Proximal Policy Optimization with a Dual Network Architecture
Prior+Duel noop	479197.0	Dueling Network Architectures for Deep Reinforcement Learning
A3C LSTM hs	470310.5	Asynchronous Methods for Deep Reinforcement Learning
A2C + SIL	461522.4	Self-Imitation Learning
Prior+Duel hs	447408.6	Deep Reinforcement Learning with Double Q-learning

0 of 42 row(s) selected.