MRS: Multi-Resolution Skills for HRL Agents

arXiv:2505.21410v2 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a performance gap on tasks requiring agility. We identify a root cause: in subgoal-based HRL, the manager's goal representation is typically learned without constraints on reachability or temporal distance from the current state, preventing precise local subgoal selection. We further show that the optimal subgoal distance is both task- and state-dependent: nearby subgoals enable precise control but amplify prediction noise, while distant subgoals produce smoother motion at the cost of geometric precision. We propose Multi-Resolution Skills (MRS), which learns multiple goal-prediction modules each specialized to a fixed temporal horizon, with a jointly trained meta-controller that selects among them based on the current state. MRS consistently outperforms fixed-resolution baselines and significantly reduces the performance gap between HRL and non-HRL state-of-the-art on DeepMind Control Suite, Gym-Robotics, and long-horizon AntMaze tasks. [Project page: https://sites.google.com/view/multi-res-skills/home]

Related

• Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents
• ARM: Advantage Reward Modeling for Long-Horizon Manipulation
• Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior
• Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach

Source: arXiv cs.AI | 2026-04-22