SOURCE-LINKED INTELLIGENCE

Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time may introduce practical subgoal management difficulties. An alternative paradigm utilizes a high-level planner to assist learning, while the policy remains conditioned only on the final goal, enabling planner-free deployment. Among these methods, Reinforcement Learning with Imagined Subgoals (RIS) introduces a regularization term that encourages the policy to take the same actions for the final goal as it does for a

Read original source ↗ Open in workspace

recordType

paper

region

Global