MP-DQN

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games3 results

Control with Prametrised ActionsonPlatform
Return· 2019-05-10
0.987
SOTA
Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces arXiv:1905.04388
Control with Prametrised ActionsonRobot Soccer Goal
Goal Probability· 2019-05-10
0.789
SOTA
Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces arXiv:1905.04388
Control with Prametrised ActionsonHalf Field Offence
Goal Probability· 2019-05-10
0.913
SOTA
Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces arXiv:1905.04388