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 Gopher

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
QR-DQN-1113585Distributional Reinforcement Learning with Quantile Regression-
Prior hs34858.8Prioritized Experience Replay-
A3C FF hs10022.8Asynchronous Methods for Deep Reinforcement Learning-
UCT20560The Arcade Learning Environment: An Evaluation Platform for General Agents-
Nature DQN8520.0Human level control through deep reinforcement learning
Gorila4373.0Massively Parallel Methods for Deep Reinforcement Learning-
DQN noop8777.4Deep Reinforcement Learning with Double Q-learning-
ES FF (1 hour) noop582.0Evolution Strategies as a Scalable Alternative to Reinforcement Learning-
SARSA2368.0--
IMPALA (deep)66782.30IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures-
Prior+Duel noop104368.2Dueling Network Architectures for Deep Reinforcement Learning-
Duel noop15718.4Dueling Network Architectures for Deep Reinforcement Learning-
POP3D6207Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization-
DDQN (tuned) noop14840.8Dueling Network Architectures for Deep Reinforcement Learning-
GDI-H3473560Generalized Data Distribution Iteration-
DDQN+Pop-Art noop56218.2Learning values across many orders of magnitude-
CGP1696Evolving simple programs for playing Atari games-
DDQN (tuned) hs15253.0Deep Reinforcement Learning with Double Q-learning-
Persistent AL10611.81Increasing the Action Gap: New Operators for Reinforcement Learning-
MuZero (Res2 Adam)122882.5Online and Offline Reinforcement Learning by Planning with a Learned Model-
0 of 43 row(s) selected.