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 River Raid

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
A3C LSTM hs6591.9Asynchronous Methods for Deep Reinforcement Learning
GDI-I328075Generalized Data Distribution Iteration-
Duel noop21162.6Dueling Network Architectures for Deep Reinforcement Learning
Gorila5310.3Massively Parallel Methods for Deep Reinforcement Learning
Nature DQN8316.0Human level control through deep reinforcement learning
MuZero323417.18Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
C51 noop17322.0A Distributional Perspective on Reinforcement Learning
DDQN+Pop-Art noop12530.8Learning values across many orders of magnitude-
DQN hs4748.5Deep Reinforcement Learning with Double Q-learning
UCT4449The Arcade Learning Environment: An Evaluation Platform for General Agents
DDQN (tuned) noop14884.5Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop20607.6Dueling Network Architectures for Deep Reinforcement Learning
DNA16789DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C FF hs12201.8Asynchronous Methods for Deep Reinforcement Learning
R2D245632.1Recurrent Experience Replay in Distributed Reinforcement Learning-
A3C FF (1 day) hs10001.2Asynchronous Methods for Deep Reinforcement Learning
DDQN (tuned) hs10838.4Deep Reinforcement Learning with Double Q-learning
FQF23560.7Fully Parameterized Quantile Function for Distributional Reinforcement Learning
GDI-H328349Generalized Data Distribution Iteration-
ES FF (1 hour) noop5009.0Evolution Strategies as a Scalable Alternative to Reinforcement Learning
0 of 41 row(s) selected.