HyperAIHyperAI초신경

Command Palette

Search for a command to run...

플랫폼

Atari Games On Atari 2600 Centipede

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
Go-Explore1422628First return, then explore
GDI-H3(1B frames)1359533GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning
MuZero1159049.27Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)874301.64Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2599140.3Recurrent Experience Replay in Distributed Reinforcement Learning
Agent57412847.86Agent57: Outperforming the Atari Human Benchmark
GDI-H3195630Generalized Data Distribution Iteration
GDI-I3155830GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-I3155830Generalized Data Distribution Iteration
Full Tree125123The Arcade Learning Environment: An Evaluation Platform for General Agents
DNA100194DNA: Proximal Policy Optimization with a Dual Network Architecture
DDQN+Pop-Art noop49065.8Learning values across many orders of magnitude
CGP24708Evolving simple programs for playing Atari games
Ape-X12974Distributed Prioritized Experience Replay
QR-DQN-112447Distributional Reinforcement Learning with Quantile Regression
DreamerV211883Mastering Atari with Discrete World Models
IQN11561Implicit Quantile Networks for Distributional Reinforcement Learning
IMPALA (deep)11049.75IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
C51 noop9646.0A Distributional Perspective on Reinforcement Learning
Best Learner8803.8The Arcade Learning Environment: An Evaluation Platform for General Agents
0 of 45 row(s) selected.
Atari Games On Atari 2600 Centipede | SOTA | HyperAI초신경