Research map / Reinforcement learning / Policy gradient and actor-critic
Model Learning for Look-Ahead Exploration in Continuous Control
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace epsilon-greedy exploration with skill-dynamics look-ahead exploration | DDPG with HER · Pick and Move, Put A inside B, Stack A on top of B, and Take A out of B | success | Helped |
| Use parameterized skills as exploration guidance rather than as macro-actions composing the policy | HERLASE · Put A inside B | success | Helped |
| Use the full skill set instead of omitting transit (ablation) | HERLASE · Pick and Move | success | Helped |
| Omit transit while retaining grasp and transfer (ablation) | HERLASE · Put A inside B | success | No clear effect |
| Omit grasp while retaining transit and transfer (ablation) | HERLASE · Put A inside B | success | Hurt |
| Use look-ahead exploration with incorrect skill dynamics due to an added insurmountable wall (ablation) | HERLASE · Put A inside B with an insurmountable wall | success | Helped |
| Increase the search branching factor beyond 5 (ablation) | HERLASE · MuJoCo manipulation tasks | seconds per episode: 17 seconds -> 71 seconds; 17 seconds -> 286 seconds | Hurt |
| Increase the search branching factor beyond 5 (ablation) | HERLASE · MuJoCo manipulation tasks | learning performance | No clear effect |
Closest papers by meaning
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 2025 · similarity 0.89)
- Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction (ICLR 2025 · similarity 0.89)
- Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning (ICML 2025 · similarity 0.88)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.88)
- ASID: Active Exploration for System Identification in Robotic Manipulation (ICLR 2024 · similarity 0.88)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 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.