Atari Games On Atari 2600 Star Gunner

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
Prior noop	63302.0	Prioritized Experience Replay
Bootstrapped DQN	55725	Deep Exploration via Bootstrapped DQN
Gorila	14919.2	Massively Parallel Methods for Deep Reinforcement Learning
GDI-I3	465750	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
SARSA	9.4	Human level control through deep reinforcement learning
Advantage Learning	61353.59	Increasing the Action Gap: New Operators for Reinforcement Learning
POP3D	48984	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Prior+Duel noop	125117.0	Dueling Network Architectures for Deep Reinforcement Learning
GDI-H3	677590	Generalized Data Distribution Iteration	-
A3C FF (1 day) hs	64393.0	Asynchronous Methods for Deep Reinforcement Learning
C51 noop	49095.0	A Distributional Perspective on Reinforcement Learning
Nature DQN	57997.0	Human level control through deep reinforcement learning
Prior hs	61582.0	Prioritized Experience Replay
DreamerV2	7800	Mastering Atari with Discrete World Models
R2D2	717344.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Duel noop	89238.0	Dueling Network Architectures for Deep Reinforcement Learning
DDQN+Pop-Art noop	589.0	Learning values across many orders of magnitude	-
CGP	2320	Evolving simple programs for playing Atari games
NoisyNet-Dueling	75867	Noisy Networks for Exploration
A2C + SIL	31309.2	Self-Imitation Learning

0 of 43 row(s) selected.