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 James Bond

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
Duel noop1312.5Dueling Network Architectures for Deep Reinforcement Learning-
Prior hs3961.0Prioritized Experience Replay-
Rational DQN Average1122Adaptive Rational Activations to Boost Deep Reinforcement Learning-
R2D225354.0Recurrent Experience Replay in Distributed Reinforcement Learning-
DreamerV240445Mastering Atari with Discrete World Models-
Recurrent Rational DQN Average1137Adaptive Rational Activations to Boost Deep Reinforcement Learning-
CGP6130Evolving simple programs for playing Atari games-
Duel hs835.5Dueling Network Architectures for Deep Reinforcement Learning-
Prior noop5148.0Prioritized Experience Replay-
Best Learner202.8The Arcade Learning Environment: An Evaluation Platform for General Agents-
GDI-I3594500Generalized Data Distribution Iteration-
A2C + SIL310.8Self-Imitation Learning-
Ape-X21322.5Distributed Prioritized Experience Replay-
IQN35108Implicit Quantile Networks for Distributional Reinforcement Learning-
DNA14102DNA: Proximal Policy Optimization with a Dual Network Architecture-
Agent57135784.96Agent57: Outperforming the Atari Human Benchmark-
Prior+Duel noop812.0Dueling Network Architectures for Deep Reinforcement Learning-
IMPALA (deep)601.50IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures-
SAC68.3Soft Actor-Critic for Discrete Action Settings-
GDI-I3594500GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
0 of 45 row(s) selected.