HyperAIHyperAI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
HyperAIHyperAI超神经

Atari Games On Atari 2600 Private Eye

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
GDI-I315100GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
DQNMMCe+SR99.1Count-Based Exploration with the Successor Representation-
DDQN (tuned) hs-575.5Deep Reinforcement Learning with Double Q-learning-
Go-Explore95756First return, then explore-
A2C + SIL661.2Self-Imitation Learning-
DQN noop146.7Deep Reinforcement Learning with Double Q-learning-
DreamerV22198Mastering Atari with Discrete World Models-
A3C FF hs206.9Asynchronous Methods for Deep Reinforcement Learning-
C51 noop15095.0A Distributional Perspective on Reinforcement Learning-
R2D25322.7Recurrent Experience Replay in Distributed Reinforcement Learning-
Prior hs670.7Prioritized Experience Replay-
GDI-H315100Generalized Data Distribution Iteration-
GDI-I315100Generalized Data Distribution Iteration-
QR-DQN-1350Distributional Reinforcement Learning with Quantile Regression-
SARSA86.0--
DQN-PixelCNN8358.7Count-Based Exploration with Neural Density Models-
Duel hs292.6Dueling Network Architectures for Deep Reinforcement Learning-
Prior+Duel noop206.0Dueling Network Architectures for Deep Reinforcement Learning-
Duel noop103.0Dueling Network Architectures for Deep Reinforcement Learning-
Prior noop200.0Prioritized Experience Replay-
0 of 52 row(s) selected.