You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Pytorch implementation of DDPG for continuous control with policy networks that share weights for structural equivalent parts (e.g. legs or arms of a humanoid).
About
Deep Reinforcement Learning for continuous control with weight sharing for structural equivalent parts.