Atari Games On Atari 2600 Amidar

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	29660.08	Agent57: Outperforming the Atari Human Benchmark
R2D2	29321.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero	28634.39	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Ape-X	8659.2	Distributed Prioritized Experience Replay
NoisyNet-Dueling	3537	Noisy Networks for Exploration
FQF	3165.3	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
IQN	2946	Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV2	2577	Mastering Atari with Discrete World Models
Duel noop	2354.5	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	2296.8	Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN	2232.3	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior noop	1838.9	Prioritized Experience Replay
DDQN (tuned) noop	1793.3	Dueling Network Architectures for Deep Reinforcement Learning
C51 noop	1735.0	A Distributional Perspective on Reinforcement Learning
QR-DQN-1	1641	Distributional Reinforcement Learning with Quantile Regression
Advantage Learning	1557.43	Increasing the Action Gap: New Operators for Reinforcement Learning
IMPALA (deep)	1554.79	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Persistent AL	1451.65	Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-I3	1442	Generalized Data Distribution Iteration	-
A2C + SIL	1362	Self-Imitation Learning

0 of 48 row(s) selected.