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 Atlantis

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
IQN978200Implicit Quantile Networks for Distributional Reinforcement Learning
C51 noop841075.0A Distributional Perspective on Reinforcement Learning
DDQN (tuned) noop106056.0Dueling Network Architectures for Deep Reinforcement Learning
Duel noop382572.0Dueling Network Architectures for Deep Reinforcement Learning
NoisyNet-Dueling972175Noisy Networks for Exploration
Ape-X944497.5Distributed Prioritized Experience Replay
Prior noop357324.0Prioritized Experience Replay
GDI-I33803000Generalized Data Distribution Iteration-
Persistent AL1465250Increasing the Action Gap: New Operators for Reinforcement Learning
UCT193858The Arcade Learning Environment: An Evaluation Platform for General Agents
Bootstrapped DQN994500Deep Exploration via Bootstrapped DQN
ASL DDQN947275Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
A3C LSTM hs875822.0Asynchronous Methods for Deep Reinforcement Learning
QR-DQN-1971850Distributional Reinforcement Learning with Quantile Regression
ES FF (1 hour) noop1267410.0Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Nature DQN85641.0Human level control through deep reinforcement learning
Advantage Learning553591.67Increasing the Action Gap: New Operators for Reinforcement Learning
DDQN (tuned) hs319688.0Deep Reinforcement Learning with Double Q-learning
Agent571528841.76Agent57: Outperforming the Atari Human Benchmark
POP3D2193605.67Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
0 of 42 row(s) selected.