HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Atari Games On Atari 2600 Centipede

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Score
Paper TitleRepository
GDI-I3155830GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
A2C + SIL7559.5Self-Imitation Learning
Bootstrapped DQN4553.5Deep Exploration via Bootstrapped DQN
DQN noop4657.7Deep Reinforcement Learning with Double Q-learning
Prior+Duel hs5570.2Deep Reinforcement Learning with Double Q-learning
GDI-I3155830Generalized Data Distribution Iteration-
MuZero (Res2 Adam)874301.64Online and Offline Reinforcement Learning by Planning with a Learned Model
ES FF (1 hour) noop7783.9Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Duel hs4881.0Dueling Network Architectures for Deep Reinforcement Learning
A3C FF (1 day) hs3306.5Asynchronous Methods for Deep Reinforcement Learning
Go-Explore1422628First return, then explore
A3C LSTM hs1997.0Asynchronous Methods for Deep Reinforcement Learning
C51 noop9646.0A Distributional Perspective on Reinforcement Learning
R2D2599140.3Recurrent Experience Replay in Distributed Reinforcement Learning-
DQN hs3973.9Deep Reinforcement Learning with Double Q-learning
Persistent AL4539.55Increasing the Action Gap: New Operators for Reinforcement Learning
DDQN (tuned) hs3853.5Deep Reinforcement Learning with Double Q-learning
Gorila6296.9Massively Parallel Methods for Deep Reinforcement Learning
SARSA4647.0--
GDI-H3195630Generalized Data Distribution Iteration-
0 of 45 row(s) selected.