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

模型名称	Score	Paper Title	Repository
Rational DQN Average	149712	Adaptive Rational Activations to Boost Deep Reinforcement Learning	-
DQN hs	154414.1	Deep Reinforcement Learning with Double Q-learning	-
Prior+Duel hs	447408.6	Deep Reinforcement Learning with Double Q-learning	-
POP3D	37780.7	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
DDQN (tuned) hs	367823.7	Deep Reinforcement Learning with Double Q-learning	-
C51 noop	949604.0	A Distributional Perspective on Reinforcement Learning	-
IMPALA (deep)	572898.27	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
Duel noop	98209.5	Dueling Network Architectures for Deep Reinforcement Learning	-
Prior hs	295972.8	Prioritized Experience Replay	-
ASL DDQN	626794	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
MuZero (Res2 Adam)	865543.44	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
Ape-X	565163.2	Distributed Prioritized Experience Replay	-
DDQN+Pop-Art noop	56287.0	Learning values across many orders of magnitude	-
DQN noop	196760.4	Deep Reinforcement Learning with Double Q-learning	-
A3C FF (1 day) hs	185852.6	Asynchronous Methods for Deep Reinforcement Learning	-
Gorila	112093.4	Massively Parallel Methods for Deep Reinforcement Learning	-
DDQN (tuned) noop	309941.9	Dueling Network Architectures for Deep Reinforcement Learning	-
ES FF (1 hour) noop	22834.8	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
R2D2	999383.2	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Prior+Duel noop	479197.0	Dueling Network Architectures for Deep Reinforcement Learning	-

0 of 42 row(s) selected.