HyperAI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
HyperAI超神经

Atari Games On Atari 2600 Video Pinball

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
Rational DQN Average149712Adaptive Rational Activations to Boost Deep Reinforcement Learning
DQN hs154414.1Deep Reinforcement Learning with Double Q-learning
Prior+Duel hs447408.6Deep Reinforcement Learning with Double Q-learning
POP3D37780.7Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
DDQN (tuned) hs367823.7Deep Reinforcement Learning with Double Q-learning
C51 noop949604.0A Distributional Perspective on Reinforcement Learning
IMPALA (deep)572898.27IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Duel noop98209.5Dueling Network Architectures for Deep Reinforcement Learning
Prior hs295972.8Prioritized Experience Replay
ASL DDQN626794Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
MuZero (Res2 Adam)865543.44Online and Offline Reinforcement Learning by Planning with a Learned Model
Ape-X565163.2Distributed Prioritized Experience Replay
DDQN+Pop-Art noop56287.0Learning values across many orders of magnitude-
DQN noop196760.4Deep Reinforcement Learning with Double Q-learning
A3C FF (1 day) hs185852.6Asynchronous Methods for Deep Reinforcement Learning
Gorila112093.4Massively Parallel Methods for Deep Reinforcement Learning
DDQN (tuned) noop309941.9Dueling Network Architectures for Deep Reinforcement Learning
ES FF (1 hour) noop22834.8Evolution Strategies as a Scalable Alternative to Reinforcement Learning
R2D2999383.2Recurrent Experience Replay in Distributed Reinforcement Learning-
Prior+Duel noop479197.0Dueling Network Architectures for Deep Reinforcement Learning
0 of 42 row(s) selected.