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 Bowling

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
Advantage Learning57.41Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-I3201.9GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
DDQN (tuned) hs69.6Deep Reinforcement Learning with Double Q-learning
DNA181DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C LSTM hs41.8Asynchronous Methods for Deep Reinforcement Learning
CGP85.8Evolving simple programs for playing Atari games
GDI-H3205.2Generalized Data Distribution Iteration-
IMPALA (deep)59.92IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Duel noop65.5Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN62.4Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
DQN noop50.4Deep Reinforcement Learning with Double Q-learning
Ape-X17.6Distributed Prioritized Experience Replay
IQN86.5Implicit Quantile Networks for Distributional Reinforcement Learning
Duel hs65.7Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-177.2Distributional Reinforcement Learning with Quantile Regression
A3C FF hs35.1Asynchronous Methods for Deep Reinforcement Learning
DDQN (tuned) noop68.1Dueling Network Architectures for Deep Reinforcement Learning
RUDDER179RUDDER: Return Decomposition for Delayed Rewards
Persistent AL71.59Increasing the Action Gap: New Operators for Reinforcement Learning
Gorila54Massively Parallel Methods for Deep Reinforcement Learning
0 of 44 row(s) selected.