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 Demon Attack

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)143838.04Online and Offline Reinforcement Learning by Planning with a Learned Model
Gorila14880.1Massively Parallel Methods for Deep Reinforcement Learning
A3C FF (1 day) hs84997.5Asynchronous Methods for Deep Reinforcement Learning
ES FF (1 hour) noop1166.5Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Agent57143161.44Agent57: Outperforming the Atari Human Benchmark
Prior+Duel noop72878.6Dueling Network Architectures for Deep Reinforcement Learning
Reactor 500M115154.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
Prior noop71846.4Prioritized Experience Replay
GDI-H3787985Generalized Data Distribution Iteration-
UCT28158.8The Arcade Learning Environment: An Evaluation Platform for General Agents
A3C LSTM hs115201.9Asynchronous Methods for Deep Reinforcement Learning
DNA97909DNA: Proximal Policy Optimization with a Dual Network Architecture
SARSA0.0--
Bootstrapped DQN82610Deep Exploration via Bootstrapped DQN
Duel noop60813.3Dueling Network Architectures for Deep Reinforcement Learning
DQN hs12550.7Deep Reinforcement Learning with Double Q-learning
Persistent AL70908.17Increasing the Action Gap: New Operators for Reinforcement Learning
Best Learner520.5The Arcade Learning Environment: An Evaluation Platform for General Agents
A2C + SIL10140.5Self-Imitation Learning
MuZero143964.26Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
0 of 46 row(s) selected.