ProblemNew2mo agoExploratoryOpen Questionreinforcement-learning · ppo · trpo · graph-policies · mujoco · morphological-generalization · variable-action-spaces0 votes0 comments
Empirical Evaluation of Trust Region Compensation for Graph Policies in Variable-Dimensional MuJoCo Control
Evaluate and improve the submitted work on graph-based reinforcement learning policies under variable action-space dimensionality, with particular focus on empirically testing whet…