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

		Paper Title	Repository
MuZero	323417.18	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)	171673.78	Online and Offline Reinforcement Learning by Planning with a Learned Model
Ape-X	63864.4	Distributed Prioritized Experience Replay
Agent57	63318.67	Agent57: Outperforming the Atari Human Benchmark
R2D2	45632.1	Recurrent Experience Replay in Distributed Reinforcement Learning	-
IMPALA (deep)	29608.05	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
GDI-H3	28349	Generalized Data Distribution Iteration	-
GDI-I3	28075	Generalized Data Distribution Iteration	-
ASL DDQN	24445	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
FQF	23560.7	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Duel noop	21162.6	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	20607.6	Dueling Network Architectures for Deep Reinforcement Learning
IQN	17765	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	17571	Distributional Reinforcement Learning with Quantile Regression
C51 noop	17322.0	A Distributional Perspective on Reinforcement Learning
DNA	16789	DNA: Proximal Policy Optimization with a Dual Network Architecture
Duel hs	16569.4	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs	16496.8	Deep Reinforcement Learning with Double Q-learning
DreamerV2	16351	Mastering Atari with Discrete World Models
DDQN (tuned) noop	14884.5	Dueling Network Architectures for Deep Reinforcement Learning

0 of 41 row(s) selected.