HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Atari Games On Atari 2600 Defender

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Score
Paper TitleRepository
IMPALA (deep)185203.00IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Prior+Duel noop41324.5Dueling Network Architectures for Deep Reinforcement Learning
Duel noop42214.0Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs34415.0Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN37026.5Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
GDI-H3970540Generalized Data Distribution Iteration-
Advantage Learning30643.59Increasing the Action Gap: New Operators for Reinforcement Learning
QR-DQN-147887Distributional Reinforcement Learning with Quantile Regression
DNA152768DNA: Proximal Policy Optimization with a Dual Network Architecture
Persistent AL32038.93Increasing the Action Gap: New Operators for Reinforcement Learning
MuZero839642.95Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Ape-X411943.5Distributed Prioritized Experience Replay
R2D2665792.0Recurrent Experience Replay in Distributed Reinforcement Learning-
CGP993010Evolving simple programs for playing Atari games
MuZero (Res2 Adam)557200.75Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-I3893110GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
NoisyNet-Dueling42253Noisy Networks for Exploration
GDI-I3893110Generalized Data Distribution Iteration-
IQN53537Implicit Quantile Networks for Distributional Reinforcement Learning
Reactor 500M223025.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
0 of 21 row(s) selected.