HyperAIHyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Atari Games On Atari 2600 Surround

評価指標

Score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Score
Paper TitleRepository
MuZero (Res2 Adam)9.9Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent579.5Agent57: Outperforming the Atari Human Benchmark
DNA5.3DNA: Proximal Policy Optimization with a Dual Network Architecture
Persistent AL0.72Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-H32.606Generalized Data Distribution Iteration-
IMPALA (deep)7.56IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
NoisyNet-Dueling10Noisy Networks for Exploration
GDI-I3-7.8Generalized Data Distribution Iteration-
Ape-X7.1Distributed Prioritized Experience Replay
QR-DQN-18.2Distributional Reinforcement Learning with Quantile Regression
ASL DDQN2.5Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
R2D29.9Recurrent Experience Replay in Distributed Reinforcement Learning-
IQN9.4Implicit Quantile Networks for Distributional Reinforcement Learning
MuZero9.99Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3-7.8GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
0 of 15 row(s) selected.
Atari Games On Atari 2600 Surround | SOTA | HyperAI超神経