DHP: 階層型強化学習エージェントのための離散階層計画
DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents
サブゴールの到達可能性を離散的に判定して木構造の計画を再帰的に構築する階層型強化学習手法を提案し、長期的な視覚計画の成功率とデータ効率を大幅に改善した。
著者: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Hierarchical Reinforcement Learning (HRL) agents often struggle with long-horizon visual planning due to their reliance on error-prone distance metrics. We propose Discrete Hierarchical Planning (DHP), a method that replaces continuous distance estimates with discrete reachability checks to evaluate subgoal feasibility. DHP recursively constructs tree-structured plans by decomposing long-term goals into sequences of simpler subtasks, using a novel advantage estimation strategy that inherently rewards shorter plans and generalizes beyond training depths. In addition, to address the data efficiency challenge, we introduce an exploration strategy that generates targeted training examples for the planning modules without needing expert data. Experiments in 25-room navigation environments demonstrate a 100% success rate (vs. 90% baseline). We also present an offline variant that achieves state-of-the-art results on OGBench benchmarks, with up to 71% absolute gains on giant HumanoidMaze tasks, demonstrating our core contributions are architecture-agnostic. The method also generalizes to momentum-based control tasks and requires only log N steps for replanning. Theoretical analysis and ablations validate our design choices.
