Research map / Reinforcement learning / Visual and representation RL

Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures

ICLR 2024 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a framework integrating deep reinforcement learning with classical planning by automatically inducing task substructures to handle sparse-reward goal-directed tasks.

Problem

Deep RL struggles with sparse-reward goal-directed tasks, while classical planning methods that handle hierarchical tasks usually assume pre-defined subtasks.

Approach

Combine DRL with classical planning by automatically inducing task substructures from the task, so planning over symbolic knowledge guides DRL without requiring hand-specified subtasks.

Closest papers by meaning

• SDRL: Interpretable and Data-Efficient Deep Reinforcement Learning Leveraging Symbolic Planning (AAAI 2019 · similarity 0.87)
• Learning to Synthesize Programs as Interpretable and Generalizable Policies (NeurIPS 2021 · similarity 0.87)
• Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner (ICML 2025 · similarity 0.87)
• Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
• Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning (AAAI 2024 · similarity 0.86)
• Efficient Reinforcement Learning by Discovering Neural Pathways (NeurIPS 2024 · similarity 0.86)