Research map / Reinforcement learning / Policy gradient and actor-critic
Policy Search with High-Dimensional Context Variables
Voot Tangkaratt, Herke van Hoof, Simone Parisi, Gerhard Neumann, Jan Peters, 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 |
|---|---|---|---|
| Add nuclear-norm regularization to learn a low-rank reward model | C-MORE · Quadratic cost function optimization | average reward | Improved |
| Replace nuclear-norm context reduction with PCA (ablation) | C-MORE · Quadratic cost function optimization | average reward | Hurt |
| Remove context dimensionality reduction (ablation) | C-MORE · Quadratic cost function optimization | average reward | Hurt |
| Add nuclear-norm regularization to learn a low-rank reward model | C-MORE · 2-DoF ball hitting | average reward | Improved |
| Replace nuclear-norm context reduction with PCA (ablation) | C-MORE · 2-DoF ball hitting | average reward | Hurt |
| Use C-REPS with PCA instead of C-MORE with nuclear-norm regularization | 2-DoF ball hitting · 2-DoF ball hitting | average reward | Mixed |
| Add nuclear-norm regularization to learn a low-rank reward model | C-MORE · 6-DoF ball hitting | average reward | Improved |
| Replace nuclear-norm context reduction with PCA (ablation) | C-MORE · 6-DoF ball hitting | average reward | Hurt |
| Use PCA to reduce context dimensions rather than the full set of principal components (ablation) | C-MORE Ridge+PCA · Quadratic cost function optimization | average reward | Mixed |
Closest papers by meaning
- High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization (NeurIPS 2020 · similarity 0.91)
- Cost-Aware Near-Optimal Policy Learning (AAAI 2025 · similarity 0.84)
- STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning (ICLR 2025 · similarity 0.84)
- Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach (ICML 2025 · similarity 0.82)
- Pre-Trained Policy Discriminators are General Reward Models (NeurIPS 2025 · similarity 0.82)
- Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts (NeurIPS 2025 · similarity 0.82)
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.
