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 Star Gunner

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 noop63302.0Prioritized Experience Replay-
Bootstrapped DQN55725Deep Exploration via Bootstrapped DQN-
Gorila14919.2Massively Parallel Methods for Deep Reinforcement Learning-
GDI-I3465750GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
SARSA9.4Human level control through deep reinforcement learning
Advantage Learning61353.59Increasing the Action Gap: New Operators for Reinforcement Learning-
POP3D48984Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization-
Prior+Duel noop125117.0Dueling Network Architectures for Deep Reinforcement Learning-
GDI-H3677590Generalized Data Distribution Iteration-
A3C FF (1 day) hs64393.0Asynchronous Methods for Deep Reinforcement Learning-
C51 noop49095.0A Distributional Perspective on Reinforcement Learning-
Nature DQN57997.0Human level control through deep reinforcement learning
Prior hs61582.0Prioritized Experience Replay-
DreamerV27800Mastering Atari with Discrete World Models-
R2D2717344.0Recurrent Experience Replay in Distributed Reinforcement Learning-
Duel noop89238.0Dueling Network Architectures for Deep Reinforcement Learning-
DDQN+Pop-Art noop589.0Learning values across many orders of magnitude-
CGP2320Evolving simple programs for playing Atari games-
NoisyNet-Dueling75867Noisy Networks for Exploration-
A2C + SIL31309.2Self-Imitation Learning-
0 of 43 row(s) selected.