Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
Long-horizon goal-conditioned reinforcement learning delegates control to a high-level module that proposes subgoals, but existing subgoals are implicit byproducts of value functions or latent actions, tied to the executor that produced them. We study a different object: a route-conditioned order of unavoidable stages that every successful executor must traverse, recoverable from offline trajectories and belonging to none of them. Its defining properties are topological: an unskippable stage is a separating set that every admissible path must cross, and a loop in free space forces a route choice. We read the two by homology in dimensions 0 and 1 over a transport-weighted carrier built from successful trajectories, yielding an enumerable gate set with shell-level certificates; the certified gates are what we call topological necessities. Certified gates enter the decision loop as a recursive topological gate hierarchy. Under a fixed, isomorphic free space, the object survives executor replacement: gates frozen on PointMaze data transfer without retraining to Ant and Humanoid, attaining the highest Humanoid aggregate under a unified interface (96.1), with +36.0 over a map-privileged reference on the multi-route task (p=1.4e-5); the planner saturates PointMaze (100+/-0) and matches or exceeds the strongest baselines on AntMaze (giant +22.9) and Kitchen (+15.8/+12.6).
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 10 Sep 2026.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning
- 2025OPAL: Encoding Causal Understanding of Physical Systems for Robot Learning
- 2023Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis
- 2026Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies
- 2025Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
- 2025HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
- 2024Geometric Fabrics: a Safe Guiding Medium for Policy Learning
- 2026PathBridger: Subgoal Bridges for Offline Goal-Conditioned Reinforcement Learning