Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning
Contrastive Reinforcement Learning (CRL) learns representations that estimate goal reachability, yet its policy remains conditioned on raw goals and therefore does not directly exploit the geometry encoded by its critic. We introduce Direction-Conditioned Policies (DCP), a method built around a small modification to CR...
S. Swaminathan, Damiya Gondha, Theyanesh Eswaramoorthy Rajahkrishnan et al.
· 0 citations