Atari Games On Atari 2600 Solaris

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	44199.93	Agent57: Outperforming the Atari Human Benchmark
Go-Explore	19671	First return, then explore
SND-STD	12460	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-VIC	11865	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-V	11582	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
GDI-I3	11074	Generalized Data Distribution Iteration	-
GDI-I3	11074	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-H3	9105	Generalized Data Distribution Iteration	-
CGP	8324	Evolving simple programs for playing Atari games
IQN	8007	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	6740	Distributional Reinforcement Learning with Quantile Regression
NoisyNet-Dueling	6522	Noisy Networks for Exploration
MuZero (Res2 Adam)	5132.95	Online and Offline Reinforcement Learning by Planning with a Learned Model
Advantage Learning	4785.16	Increasing the Action Gap: New Operators for Reinforcement Learning
R2D2	3787.2	Recurrent Experience Replay in Distributed Reinforcement Learning	-
ASL DDQN	3506.8	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
RND	3282	Exploration by Random Network Distillation
Ape-X	2892.9	Distributed Prioritized Experience Replay
IMPALA (deep)	2365.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DQNMMCe	2244.6	Count-Based Exploration with the Successor Representation

0 of 23 row(s) selected.