Atari Games On Atari 2600 Time Pilot

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
Advantage Learning	8969.12	Increasing the Action Gap: New Operators for Reinforcement Learning	-
A3C FF hs	12679.0	Asynchronous Methods for Deep Reinforcement Learning	-
Best Learner	3741.2	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
GDI-I3	216770	Generalized Data Distribution Iteration	-
NoisyNet-Dueling	17301	Noisy Networks for Exploration	-
DDQN (tuned) noop	8339.0	Dueling Network Architectures for Deep Reinforcement Learning	-
Duel noop	11666.0	Dueling Network Architectures for Deep Reinforcement Learning	-
POP3D	3770.33	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
Nature DQN	5947.0	Human level control through deep reinforcement learning
QR-DQN-1	10345	Distributional Reinforcement Learning with Quantile Regression	-
DNA	12774	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
Rational DQN Average	17632	Adaptive Rational Activations to Boost Deep Reinforcement Learning	-
MuZero	476763.90	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
UCT	63854.5	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
ES FF (1 hour) noop	4970.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
IDVQ + DRSC + XNES	4600	Playing Atari with Six Neurons	-
Bootstrapped DQN	9079.4	Deep Exploration via Bootstrapped DQN	-
R2D2	445377.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DDQN+Pop-Art noop	4870.0	Learning values across many orders of magnitude	-
CGP	12040	Evolving simple programs for playing Atari games	-

0 of 44 row(s) selected.