HyperAI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
HyperAI超神経

Atari Games On Atari 2600 Enduro

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
DQN hs626.7Deep Reinforcement Learning with Double Q-learning
Advantage Learning1252.7Increasing the Action Gap: New Operators for Reinforcement Learning
IQN2359Implicit Quantile Networks for Distributional Reinforcement Learning
DQN Best661Playing Atari with Deep Reinforcement Learning
Prior noop2093.0Prioritized Experience Replay
DNA2059DNA: Proximal Policy Optimization with a Dual Network Architecture
ASL DDQN2103.1Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
Nature DQN301.8Human level control through deep reinforcement learning
Persistent AL1343.1Increasing the Action Gap: New Operators for Reinforcement Learning
Prior+Duel noop2306.4Dueling Network Architectures for Deep Reinforcement Learning
A3C FF hs-82.5Asynchronous Methods for Deep Reinforcement Learning
A3C LSTM hs-82.5Asynchronous Methods for Deep Reinforcement Learning
CGP56.8Evolving simple programs for playing Atari games
UCT286.3The Arcade Learning Environment: An Evaluation Platform for General Agents
GDI-I314330GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
Duel hs2077.4Dueling Network Architectures for Deep Reinforcement Learning
Rational DQN Average1043Adaptive Rational Activations to Boost Deep Reinforcement Learning
DQN noop729.0Deep Reinforcement Learning with Double Q-learning
VPN382Value Prediction Network
Duel noop2258.2Dueling Network Architectures for Deep Reinforcement Learning
0 of 48 row(s) selected.