Control With Prametrised Actions On Half

Goal Probability

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
MP-DQN	0.913	Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces
Hybrid SAC	0.639	Discrete and Continuous Action Representation for Practical RL in Video Games

0 of 2 row(s) selected.