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 Alien

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
DNA5021DNA: Proximal Policy Optimization with a Dual Network Architecture-
Persistent AL5699.81Increasing the Action Gap: New Operators for Reinforcement Learning-
Prior+Duel noop3941.0Dueling Network Architectures for Deep Reinforcement Learning-
A2C + SIL2242.2Self-Imitation Learning-
A3C LSTM hs945.3Asynchronous Methods for Deep Reinforcement Learning-
GDI-H348735Generalized Data Distribution Iteration-
CGP1978Evolving simple programs for playing Atari games-
Best Learner939.2The Arcade Learning Environment: An Evaluation Platform for General Agents-
MuZero741812.63Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model-
R2D2229496.9Recurrent Experience Replay in Distributed Reinforcement Learning-
Gorila813.5Massively Parallel Methods for Deep Reinforcement Learning-
DDQN (tuned) hs1033.4Deep Reinforcement Learning with Double Q-learning-
A3C FF hs518.4Asynchronous Methods for Deep Reinforcement Learning-
Prior noop4203.8Prioritized Experience Replay-
SAC216.9Soft Actor-Critic for Discrete Action Settings-
Duel noop4461.4Dueling Network Architectures for Deep Reinforcement Learning-
DDQN (tuned) noop3747.7Dueling Network Architectures for Deep Reinforcement Learning-
Reactor 500M12689.1The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
GDI-H3(1B frames)279700GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning-
Bootstrapped DQN2436.6Deep Exploration via Bootstrapped DQN-
0 of 49 row(s) selected.