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 Bank Heist

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 hs1004.6Deep Reinforcement Learning with Double Q-learning-
Rainbow+SEER276.6Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings-
NoisyNet-Dueling1318Noisy Networks for Exploration-
MuZero (Res2 Adam)27219.8Online and Offline Reinforcement Learning by Planning with a Learned Model-
Best Learner190.8The Arcade Learning Environment: An Evaluation Platform for General Agents-
DNA1286DNA: Proximal Policy Optimization with a Dual Network Architecture-
DDQN (tuned) noop1030.6Dueling Network Architectures for Deep Reinforcement Learning-
Gorila399.4Massively Parallel Methods for Deep Reinforcement Learning-
DQN hs312.7Deep Reinforcement Learning with Double Q-learning-
Duel hs1129.3Dueling Network Architectures for Deep Reinforcement Learning-
POP3D1212.23Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization-
DreamerV21126Mastering Atari with Discrete World Models-
DDQN+Pop-Art noop1103.3Learning values across many orders of magnitude-
SARSA67.4--
DDQN (tuned) hs886.0Deep Reinforcement Learning with Double Q-learning-
Bootstrapped DQN1208Deep Exploration via Bootstrapped DQN-
Advantage Learning633.63Increasing the Action Gap: New Operators for Reinforcement Learning-
CURL193.7CURL: Contrastive Unsupervised Representations for Reinforcement Learning-
Discrete Latent Space World Model (VQ-VAE)121.6Smaller World Models for Reinforcement Learning-
IQN1416Implicit Quantile Networks for Distributional Reinforcement Learning-
0 of 45 row(s) selected.