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 Tennis

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
SARSA0.0--
Duel noop5.1Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN22.3Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
Recurrent Rational DQN Average20.6Adaptive Rational Activations to Boost Deep Reinforcement Learning
POP3D-8.32Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
R2D2-0.1Recurrent Experience Replay in Distributed Reinforcement Learning-
Rational DQN Average20.5Adaptive Rational Activations to Boost Deep Reinforcement Learning
GDI-I324GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
Nature DQN-2.5Human level control through deep reinforcement learning
Agent5723.84Agent57: Outperforming the Atari Human Benchmark
DQN noop12.2Deep Reinforcement Learning with Double Q-learning
IQN23.6Implicit Quantile Networks for Distributional Reinforcement Learning
UCT2.8The Arcade Learning Environment: An Evaluation Platform for General Agents
Gorila-0.7Massively Parallel Methods for Deep Reinforcement Learning
A3C LSTM hs-6.4Asynchronous Methods for Deep Reinforcement Learning
Prior hs-5.3Prioritized Experience Replay
MuZero0.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
ES FF (1 hour) noop-4.5Evolution Strategies as a Scalable Alternative to Reinforcement Learning
QR-DQN-123.6Distributional Reinforcement Learning with Quantile Regression
DQN hs11.1Deep Reinforcement Learning with Double Q-learning
0 of 43 row(s) selected.