
MN
Madeleine Nouri, Gelareh Mohammadi, Francisco Cruz
· 1 min read
ResearcharXiv cs.AI
Demonstration-Free Skill Composition for Navigation and Manipulation
arXiv:2611.25462v1 Announce Type: cross
Abstract: Hierarchical reinforcement learning enables sequential tasks to be represented as compositions of separately trained skills. This paper evaluates demonstration-free hierarchical pipelines for MiniGrid navigation and robotic manipulation, comparing their training requirements and task performance with flat reinforcement learning baselines. The evaluation concerns complete pipelines with task-specific observation, reward and control structures. In navigation, two parameterised skills are reused across unseen FourRooms layouts under manually specified high-level plans. In manipulation, reaching, grasp alignment and lifting are trained separately, with downstream skills initialised from states collected during predecessor rollouts. Across unseen navigation layouts, the hierarchical pipeline substantially outperforms the evaluated flat DQN baselines while requiring fewer training interactions. In manipulation, the hierarchical chain requires fewer training steps than flat SAC and exhibits lower observed variation across seeds. The frozen Pick and Lift skills are further reused for stacking by training an additional Place skill.
Original source
This story was published by arXiv cs.AI and written by Madeleine Nouri, Gelareh Mohammadi, Francisco Cruz. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


