Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning
S K Swaminathan, Damiya Gondha, Theyanesh Eswaramoorthy Rajahkrishnan +1
Contrastive Reinforcement Learning (CRL) learns representations that estimate goal reachability, yet its policy remains conditioned on raw goals and therefore does not directly exp…
cs.LG2026
Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning
Swaminathan S K, Damiya Gondha, Theyanesh Eswaramoorthy Rajahkrishnan +1
Hamilton-Jacobi-Bellman theory implies that the optimal goal-conditioned action depends on the goal only through the gradient of the goal-reaching distance at the current state, ye…