Research map / Reinforcement learning / Policy gradient and actor-critic
Multi-Step Generalized Policy Improvement by Leveraging Approximate Models
Lucas Nunes Alegre, Ana L. C. Bazzan, Ann Nowe, Bruno Castro da Silva
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 |
|---|---|---|---|
| increase planning horizon h in h-GPI (1-GPI up to 10-GPI) over standard GPI (h=0) | h-GPI with SFs · stochastic FourRoom test tasks | normalized return (median, IQM, mean) | Improved |
| add GPI bootstrapping at step h (h-GPI vs SF-MPC without bootstrapping) (ablation) | SF-based MPC · stochastic FourRoom | normalized return | Improved |
| add Gaussian noise to learned SFs (std 0.05, 0.1, 0.2) on standard GPI (h=0) (ablation) | GPI · FourRoom with noisy SFs | mean normalized return | Hurt |
| increase h to compensate for noise in SFs (ablation) | h-GPI · FourRoom with noisy SFs | mean normalized return | Improved |
| use h-GPI instead of GPI over training tasks | USFA-based GPI · Reacher | normalized return | Improved |
| add constraints on value estimates (CGPI) over GPI-ST | GPI-ST · Reacher and FetchPush | normalized return | No clear effect |
| use h-GPI instead of SF-MPC with up to 15 planning steps | SF-MPC · FetchPush | normalized return | Improved |
| increase h to intermediate values in h-GPI | h-GPI · FetchPush | normalized return | Mixed |
Closest papers by meaning
- Constructing an Optimal Behavior Basis for the Option Keyboard (NeurIPS 2025 · similarity 0.89)
- Distributional Successor Features Enable Zero-Shot Policy Optimization (NeurIPS 2024 · similarity 0.89)
- Provable Zero-Shot Generalization in Offline Reinforcement Learning (ICML 2025 · similarity 0.88)
- Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract) (AAAI 2024 · similarity 0.88)
- On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Model-Based Transfer Learning for Contextual Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
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.
