Atari Games On Atari 2600 Pitfall

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

模型名称	Score	Paper Title	Repository
NoisyNet-Dueling	0	Noisy Networks for Exploration	-
Go-Explore	6954	First return, then explore	-
POP3D	0	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
QR-DQN-1	0	Distributional Reinforcement Learning with Quantile Regression	-
IQN	0	Implicit Quantile Networks for Distributional Reinforcement Learning	-
DNA	0	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
Advantage Learning	0	Increasing the Action Gap: New Operators for Reinforcement Learning	-
MuZero (Res2 Adam)	0	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
SND-V	0	Self-supervised network distillation: an effective approach to exploration in sparse reward environments	-
MuZero	0.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
SND-VIC	0	Self-supervised network distillation: an effective approach to exploration in sparse reward environments	-
DreamerV2	0	Mastering Atari with Discrete World Models	-
CGP	0	Evolving simple programs for playing Atari games	-
GDI-H3	-4.345	Generalized Data Distribution Iteration	-
Ape-X	-0.6	Distributed Prioritized Experience Replay	-
Go-Explore	102571	Go-Explore: a New Approach for Hard-Exploration Problems	-
ASL DDQN	0	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
IMPALA (deep)	-1.66	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
R2D2	0.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
RND	-3	Exploration by Random Network Distillation	-

0 of 23 row(s) selected.