HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Atari Games On Atari 2600 Kung Fu Master

评估指标

Score

评测结果

各个模型在此基准测试上的表现结果

模型名称
Score
Paper TitleRepository
Prior noop39581.0Prioritized Experience Replay
DQN hs20882.0Deep Reinforcement Learning with Double Q-learning
DDQN (tuned) noop29710.0Dueling Network Architectures for Deep Reinforcement Learning
A3C LSTM hs40835.0Asynchronous Methods for Deep Reinforcement Learning
Advantage Learning32182.99Increasing the Action Gap: New Operators for Reinforcement Learning
Prior+Duel noop48375.0Dueling Network Architectures for Deep Reinforcement Learning
A3C FF (1 day) hs3046.0Asynchronous Methods for Deep Reinforcement Learning
GDI-I3140440Generalized Data Distribution Iteration-
FQF111138.5Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DDQN (tuned) hs30207.0Deep Reinforcement Learning with Double Q-learning
Bootstrapped DQN36733.3Deep Exploration via Bootstrapped DQN
DDQN+Pop-Art noop34393.0Learning values across many orders of magnitude-
CGP57400Evolving simple programs for playing Atari games
POP3D33728Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Persistent AL34650.91Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-H3 (200M)1666000GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning-
DreamerV262741Mastering Atari with Discrete World Models
NoisyNet-Dueling41672Noisy Networks for Exploration
Gorila20620.0Massively Parallel Methods for Deep Reinforcement Learning
DQN noop26059.0Deep Reinforcement Learning with Double Q-learning
0 of 43 row(s) selected.