Research map / Reinforcement learning / Policy gradient and actor-critic
Hierarchical Policy Search via Return-Weighted Density Estimation
Takayuki Osa, Masashi Sugiyama
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 HPSDE instead of HiREPS | Hierarchical policy search · Toy problems with two- and three-mode returns | return | Improved |
| identify option structure with HPSDE instead of HiREPS | Hierarchical policy search · Toy problems with two- and three-mode returns | speed of optimizing the number of option policies | Improved |
| use GP-based gating instead of softmax gating (ablation) | HPSDE · Toy problems with two- and three-mode returns | return | Improved |
| use REPS instead of RWR to update option policies (ablation) | HPSDE · Toy problems with two- and three-mode returns | learning performance | No clear effect |
| use HiREPS instead of HPSDE | Hierarchical policy search · Puddle world | return | Hurt |
| use HPSDE with REPS and GP gating | HPSDE · Redundant-manipulator motion planning | return | Improved |
| use HPSDE instead of HiREPS | Hierarchical policy search · Redundant-manipulator motion planning | return | Mixed |
Closest papers by meaning
- Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization (ICLR 2019 · similarity 0.90)
- Data-Efficient Hierarchical Reinforcement Learning (NeurIPS 2018 · similarity 0.90)
- On Efficiency in Hierarchical Reinforcement Learning (NeurIPS 2020 · similarity 0.90)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · similarity 0.88)
- Deep Reinforcement Learning from Hierarchical Preference Design (ICML 2025 · similarity 0.87)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.87)
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.
