Atari Games On Atari 2600 Fishing Derby

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	91.16	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	86.97	Agent57: Outperforming the Atari Human Benchmark
R2D2	85.8	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero (Res2 Adam)	73.94	Online and Offline Reinforcement Learning by Planning with a Learned Model
DreamerV2	65	Mastering Atari with Discrete World Models
GDI-H3	65	Generalized Data Distribution Iteration	-
GDI-I3	59	Generalized Data Distribution Iteration	-
GDI-I3	59	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
DNA	57.4	DNA: Proximal Policy Optimization with a Dual Network Architecture
NoisyNet-Dueling	57	Noisy Networks for Exploration
A2C + SIL	55.8	Self-Imitation Learning
FQF	52.7	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Duel noop	46.4	Dueling Network Architectures for Deep Reinforcement Learning
DDQN+Pop-Art noop	45.1	Learning values across many orders of magnitude	-
IMPALA (deep)	44.85	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Ape-X	44.4	Distributed Prioritized Experience Replay
Prior+Duel noop	41.3	Dueling Network Architectures for Deep Reinforcement Learning
Prior noop	39.5	Prioritized Experience Replay
QR-DQN-1	39	Distributional Reinforcement Learning with Quantile Regression
UCT	37.8	The Arcade Learning Environment: An Evaluation Platform for General Agents

0 of 44 row(s) selected.