Atari Games On Atari 2600 Private Eye

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
GDI-I3	15100	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
DQNMMCe+SR	99.1	Count-Based Exploration with the Successor Representation
DDQN (tuned) hs	-575.5	Deep Reinforcement Learning with Double Q-learning
Go-Explore	95756	First return, then explore
A2C + SIL	661.2	Self-Imitation Learning
DQN noop	146.7	Deep Reinforcement Learning with Double Q-learning
DreamerV2	2198	Mastering Atari with Discrete World Models
A3C FF hs	206.9	Asynchronous Methods for Deep Reinforcement Learning
C51 noop	15095.0	A Distributional Perspective on Reinforcement Learning
R2D2	5322.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Prior hs	670.7	Prioritized Experience Replay
GDI-H3	15100	Generalized Data Distribution Iteration	-
GDI-I3	15100	Generalized Data Distribution Iteration	-
QR-DQN-1	350	Distributional Reinforcement Learning with Quantile Regression
SARSA	86.0	-	-
DQN-PixelCNN	8358.7	Count-Based Exploration with Neural Density Models
Duel hs	292.6	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	206.0	Dueling Network Architectures for Deep Reinforcement Learning
Duel noop	103.0	Dueling Network Architectures for Deep Reinforcement Learning
Prior noop	200.0	Prioritized Experience Replay

0 of 52 row(s) selected.