Atari Games On Atari 2600 Centipede

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
GDI-I3	155830	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
A2C + SIL	7559.5	Self-Imitation Learning
Bootstrapped DQN	4553.5	Deep Exploration via Bootstrapped DQN
DQN noop	4657.7	Deep Reinforcement Learning with Double Q-learning
Prior+Duel hs	5570.2	Deep Reinforcement Learning with Double Q-learning
GDI-I3	155830	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	874301.64	Online and Offline Reinforcement Learning by Planning with a Learned Model
ES FF (1 hour) noop	7783.9	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Duel hs	4881.0	Dueling Network Architectures for Deep Reinforcement Learning
A3C FF (1 day) hs	3306.5	Asynchronous Methods for Deep Reinforcement Learning
Go-Explore	1422628	First return, then explore
A3C LSTM hs	1997.0	Asynchronous Methods for Deep Reinforcement Learning
C51 noop	9646.0	A Distributional Perspective on Reinforcement Learning
R2D2	599140.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DQN hs	3973.9	Deep Reinforcement Learning with Double Q-learning
Persistent AL	4539.55	Increasing the Action Gap: New Operators for Reinforcement Learning
DDQN (tuned) hs	3853.5	Deep Reinforcement Learning with Double Q-learning
Gorila	6296.9	Massively Parallel Methods for Deep Reinforcement Learning
SARSA	4647.0	-	-
GDI-H3	195630	Generalized Data Distribution Iteration	-

0 of 45 row(s) selected.