Atari Games On Atari 2600 Montezumas Revenge

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
Go-Explore	43791	First return, then explore
Go-Explore	43763	Go-Explore: a New Approach for Hard-Exploration Problems
SND-V	21565	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
Agent57	9352.01	Agent57: Outperforming the Atari Human Benchmark
RND	8152	Exploration by Random Network Distillation
SND-VIC	7838	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-STD	7212	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
A2C+CoEX	6635	Contingency-Aware Exploration in Reinforcement Learning	-
DQN-PixelCNN	3705.5	Count-Based Exploration with Neural Density Models
DDQN-PC	3459	Unifying Count-Based Exploration and Intrinsic Motivation
GDI-I3	3000	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	3000	Generalized Data Distribution Iteration	-
Sarsa-φ-EB	2745.4	Count-Based Exploration in Feature Space for Reinforcement Learning
Intrinsic Reward Agent	2504.6	Large-Scale Study of Curiosity-Driven Learning
GDI-H3	2500	Generalized Data Distribution Iteration	-
Ape-X	2500.0	Distributed Prioritized Experience Replay
MuZero (Res2 Adam)	2500	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	2061.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DQN+SR	1778.8	Count-Based Exploration with the Successor Representation
DQNMMCe+SR	1778.6	Count-Based Exploration with the Successor Representation

0 of 50 row(s) selected.