Atari Games On Atari 2600 Qbert

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
Prior+Duel noop	18760.3	Dueling Network Architectures for Deep Reinforcement Learning
MuZero	72276.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Duel hs	14175.8	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs	14063.0	Deep Reinforcement Learning with Double Q-learning
C51 noop	23784	A Distributional Perspective on Reinforcement Learning
GDI-H3(200M frames)	28657	Generalized Data Distribution Iteration	-
DreamerV2	94688	Mastering Atari with Discrete World Models
Prior noop	16256.5	Prioritized Experience Replay
IQN	25750	Implicit Quantile Networks for Distributional Reinforcement Learning
DDQN (tuned) noop	15088.5	Dueling Network Architectures for Deep Reinforcement Learning
VPN	14517	Value Prediction Network
Sarsa-ε	3895.3	Count-Based Exploration in Feature Space for Reinforcement Learning
IQ-Learn	-	IQ-Learn: Inverse soft-Q Learning for Imitation
SARSA	960.3	-	-
DQN hs	9271.5	Deep Reinforcement Learning with Double Q-learning
MAC	243.4	Mean Actor Critic
MP-EB	15805	Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
DDQN+Pop-Art noop	5236.8	Learning values across many orders of magnitude	-
DQN Best	4500	Playing Atari with Deep Reinforcement Learning
GDI-I3	27800	Generalized Data Distribution Iteration	-

0 of 57 row(s) selected.