Atari Games On Atari 2600 Robotank

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	131.13	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	127.32	Agent57: Outperforming the Atari Human Benchmark
GDI-H3	113.4	Generalized Data Distribution Iteration	-
GDI-I3	108.2	Generalized Data Distribution Iteration	-
GDI-I3	108.2	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
MuZero (Res2 Adam)	100.59	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	100.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DreamerV2	78	Mastering Atari with Discrete World Models
FQF	75.7	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Ape-X	73.8	Distributed Prioritized Experience Replay
Advantage Learning	69.31	Increasing the Action Gap: New Operators for Reinforcement Learning
Bootstrapped DQN	66.6	Deep Exploration via Bootstrapped DQN
ASL DDQN	65.8	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Duel noop	65.3	Dueling Network Architectures for Deep Reinforcement Learning
DDQN (tuned) noop	65.1	Dueling Network Architectures for Deep Reinforcement Learning
DNA	64.8	DNA: Proximal Policy Optimization with a Dual Network Architecture
DDQN+Pop-Art noop	64.3	Learning values across many orders of magnitude	-
NoisyNet-Dueling	64	Noisy Networks for Exploration
DQN noop	63.9	Deep Reinforcement Learning with Double Q-learning
Prior noop	62.6	Prioritized Experience Replay

0 of 42 row(s) selected.