Research map / Reinforcement learning / Visual and representation RL
Efficient Dialog Policy Learning by Reasoning with Contextual Knowledge
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 |
|---|---|---|---|
| Add MLN internal-knowledge reasoning to A2C (ablation) | A2C dialog policy · PyDial hotel booking | success rate | Helped |
| Add ASP external-knowledge reasoning to A2C + MLN (ablation) | A2C dialog policy · PyDial hotel booking | success rate | Helped |
| Add MLN internal-knowledge reasoning to DQN (ablation) | DQN dialog policy · PyDial hotel booking | success rate | Helped |
| Add ASP external-knowledge reasoning to DQN + MLN (ablation) | DQN dialog policy · PyDial hotel booking | success rate | Helped |
| Add MLN internal-knowledge reasoning to ACER (ablation) | ACER dialog policy · PyDial hotel booking | success rate | Helped |
| Add ASP external-knowledge reasoning to ACER + MLN (ablation) | ACER dialog policy · PyDial hotel booking | success rate | Helped |
| Add MLN internal-knowledge reasoning to BBQN (ablation) | BBQN dialog policy · PyDial hotel booking | success rate | Helped |
| Add ASP external-knowledge reasoning to BBQN + MLN (ablation) | BBQN dialog policy · PyDial hotel booking | success rate | Helped |
| Train the MLN with more user-goal samples (ablation) | A2C + MLN dialog policy · PyDial hotel booking | success rate | Helped |
| Use incomplete rather than no external knowledge (ablation) | A2C + MLN dialog policy · PyDial hotel booking | success rate | Helped |
| Use inaccurate rather than no external knowledge (ablation) | A2C + MLN dialog policy · PyDial hotel booking | success rate | Helped |
| Use incomplete or inaccurate rather than perfect external knowledge (ablation) | A2C + MLN dialog policy · PyDial hotel booking | success rate | Hurt |
Closest papers by meaning
- Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues (AAAI 2025 · similarity 0.88)
- Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents (ICLR 2024 · similarity 0.87)
- Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents (ICLR 2026 · similarity 0.86)
- Multimodal Policy Internalization for Conversational Agents (ICLR 2026 · similarity 0.86)
- Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning (AAAI 2024 · similarity 0.86)
- IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning (ICML 2026 · similarity 0.85)
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.