Research map / Reinforcement learning / Visual and representation RL
Switch-Based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Yuexin Wu, Xiujun Li, Jingjing Liu, Jianfeng Gao, Yiming Yang
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 Switch-DDQ instead of DDQ(5) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 200 | success rate: 0.7733 -> 0.8533 | Improved |
| Use Switch-DDQ instead of DDQ(5) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 300 | success rate: 0.7467 -> 0.7800 | Improved |
| Use Switch-DDQ instead of DDQ(10) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 200 | success rate: 0.6000 -> 0.8533 | Improved |
| Use Switch-DDQ instead of DDQ(10) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 300 | success rate: 0.3733 -> 0.7800 | Improved |
| Use Switch-DDQ instead of DDQ(20) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 200 | success rate: 0.4467 -> 0.8533 | Improved |
| Use Switch-DDQ instead of DDQ(20) | Movie-ticket dialogue policy learning · Movie-ticket booking simulation, epoch 300 | success rate: 0.3800 -> 0.7800 | Improved |
| Replace active user-goal sampling with uniform sampling (ablation) | Switch-DDQ · Movie-ticket booking simulation | success rate | Hurt |
| Replace active user-goal sampling with uniform sampling (ablation) | Switch-DDQ · Low-success-rate user-goal categories in movie-ticket booking simulation | success rate | Hurt |
Closest papers by meaning
- Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning (ICLR 2025 · similarity 0.87)
- Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents (ICLR 2024 · similarity 0.85)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.85)
- Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization (ICML 2026 · similarity 0.85)
- Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues (AAAI 2025 · similarity 0.85)
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF (ICLR 2025 · 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.
