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 Qbert

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+Duel noop18760.3Dueling Network Architectures for Deep Reinforcement Learning-
MuZero72276.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model-
Duel hs14175.8Dueling Network Architectures for Deep Reinforcement Learning-
Prior+Duel hs14063.0Deep Reinforcement Learning with Double Q-learning-
C51 noop23784A Distributional Perspective on Reinforcement Learning-
GDI-H3(200M frames)28657Generalized Data Distribution Iteration-
DreamerV294688Mastering Atari with Discrete World Models-
Prior noop16256.5Prioritized Experience Replay-
IQN25750Implicit Quantile Networks for Distributional Reinforcement Learning-
DDQN (tuned) noop15088.5Dueling Network Architectures for Deep Reinforcement Learning-
VPN14517Value Prediction Network-
Sarsa-ε3895.3Count-Based Exploration in Feature Space for Reinforcement Learning-
IQ-Learn-IQ-Learn: Inverse soft-Q Learning for Imitation-
SARSA960.3--
DQN hs9271.5Deep Reinforcement Learning with Double Q-learning-
MAC243.4Mean Actor Critic-
MP-EB15805Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models-
DDQN+Pop-Art noop5236.8Learning values across many orders of magnitude-
DQN Best4500Playing Atari with Deep Reinforcement Learning-
GDI-I327800Generalized Data Distribution Iteration-
0 of 57 row(s) selected.