Atari Games On Atari 2600 River Raid

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
A3C LSTM hs	6591.9	Asynchronous Methods for Deep Reinforcement Learning	-
GDI-I3	28075	Generalized Data Distribution Iteration	-
Duel noop	21162.6	Dueling Network Architectures for Deep Reinforcement Learning	-
Gorila	5310.3	Massively Parallel Methods for Deep Reinforcement Learning	-
Nature DQN	8316.0	Human level control through deep reinforcement learning
MuZero	323417.18	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
C51 noop	17322.0	A Distributional Perspective on Reinforcement Learning	-
DDQN+Pop-Art noop	12530.8	Learning values across many orders of magnitude	-
DQN hs	4748.5	Deep Reinforcement Learning with Double Q-learning	-
UCT	4449	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
DDQN (tuned) noop	14884.5	Dueling Network Architectures for Deep Reinforcement Learning	-
Prior+Duel noop	20607.6	Dueling Network Architectures for Deep Reinforcement Learning	-
DNA	16789	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
A3C FF hs	12201.8	Asynchronous Methods for Deep Reinforcement Learning	-
R2D2	45632.1	Recurrent Experience Replay in Distributed Reinforcement Learning	-
A3C FF (1 day) hs	10001.2	Asynchronous Methods for Deep Reinforcement Learning	-
DDQN (tuned) hs	10838.4	Deep Reinforcement Learning with Double Q-learning	-
FQF	23560.7	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	-
GDI-H3	28349	Generalized Data Distribution Iteration	-
ES FF (1 hour) noop	5009.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-

0 of 41 row(s) selected.