Openai Gym On Walker2D V2

Action Repetition

Average Decisions

Mean Reward

Résultats

Résultats de performance de divers modèles sur ce benchmark

				Paper Title
AWR	-	-	5813	Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
TLA	.4745	513.12	3878.41	Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures

0 of 2 row(s) selected.