Research map / Reinforcement learning / Visual and representation RL
CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
Shuang Ao, Tianyi Zhou, Guodong Long, Qinghua Lu, Liming Zhu, Jing Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use CO-PILOT's learned planner with sub-task tree on top of SAC instead of plain SAC | SAC · Maze environment | success rate | Improved |
| Mutual training of planner and RL versus SoRB's planner built on a pre-trained RL policy | SoRB · Maze/Mujoco/BipedalWalker | sample efficiency | Improved |
| Compare CO-PILOT with SoRB on final performance | SoRB · BipedalWalker | percentage of mastered tracks | No clear effect |
| Use CO-PILOT instead of hierarchical RL (HRL) | HRL · Mujoco Ant-v1 | average return | Improved |
| Vary sub-task tree depth K over 5 values (ablation) | CO-PILOT · Maze | success rate | Mixed |
| Increase planner batch size b beyond 5 (ablation) | CO-PILOT · Maze | success rate | No clear effect |
| More mutual-training episodes (Episode 1 to 5) | CO-PILOT · Maze | RL time cost per sub-task | Improved |
Closest papers by meaning
- EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning (ICML 2022 · similarity 0.89)
- Imitating Graph-Based Planning with Goal-Conditioned Policies (ICLR 2023 · similarity 0.88)
- Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs (AAAI 2026 · similarity 0.88)
- Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
- Flattening Hierarchies with Policy Bootstrapping (NeurIPS 2025 · similarity 0.87)
- Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
