Atari Games On Atari 2600 Venture

Score

Results

Performance results of various models on this benchmark

		Paper Title
Agent57	2623.71	Agent57: Outperforming the Atari Human Benchmark
Go-Explore	2281	First return, then explore
SND-VIC	2188	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-STD	2138	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
GDI-I3	2035	Generalized Data Distribution Iteration
GDI-H3	2000	Generalized Data Distribution Iteration
GDI-H3(200M frames)	2000	Generalized Data Distribution Iteration
R2D2	1970.7	Recurrent Experience Replay in Distributed Reinforcement Learning
RND	1859	Exploration by Random Network Distillation
Ape-X	1813	Distributed Prioritized Experience Replay
SND-V	1787	Self-supervised network distillation: an effective approach to exploration in sparse reward environments
MuZero (Res2 Adam)	1731.47	Online and Offline Reinforcement Learning by Planning with a Learned Model
C51 noop	1520.0	A Distributional Perspective on Reinforcement Learning
RUDDER	1350	RUDDER: Return Decomposition for Delayed Rewards
IQN	1318	Implicit Quantile Networks for Distributional Reinforcement Learning
DQNMMCe+SR	1241.8	Count-Based Exploration with the Successor Representation
DDQN+Pop-Art noop	1172.0	Learning values across many orders of magnitude
Sarsa-φ-EB	1169.2	Count-Based Exploration in Feature Space for Reinforcement Learning
NoisyNet-Dueling	815	Noisy Networks for Exploration
ES FF (1 hour) noop	760.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning

0 of 55 row(s) selected.