Research map / Reinforcement learning / Visual and representation RL
Dynamic Reward-Based Dueling Deep Dyna-Q: Robust Policy Learning in Noisy Environments
Yangyang Zhao, Zhenyu Wang, Kai Yin, Rui Zhang, Zhenhua Huang, Pei Wang
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 |
|---|---|---|---|
| replace DQN with dynamic-reward Dueling DQN inside Dyna-Q (DR-D3Q vs DDQ(20)) | DDQ(20) · Movie-ticket booking, noise 0.3, epoch 400 | success rate: 0.3169 -> 0.4120 | Improved |
| replace DQN with dynamic-reward Dueling DQN inside Dyna-Q (DR-D3Q vs DDQ(20)) | DDQ(20) · Movie-ticket booking, noise 0 (noise-free), epoch 300 | success rate: 0.7080 -> 0.7899 | Improved |
| DR-D3Q(20) vs DQN(20) upper bound with real-experience-only extra data | DR-D3Q(20) · Movie-ticket booking, noise 0.3, epoch 400 | success rate: 0.3725 -> 0.4120 | Improved |
| replace dynamic reward with original reward (D3Q, dueling only) (ablation) | DR-D3Q · Movie-ticket booking, noise 0.3 | success rate (learning curve) | Hurt |
| replace Dueling DQN with plain DQN while keeping dynamic reward (DR-DDQ) (ablation) | DR-D3Q · Movie-ticket booking, noise 0.3 | success rate (learning curve) | Hurt |
| human evaluation with 30% erroneous slots: DR-D3Q vs DDQ(20) and DQN | DR-D3Q(20) · Human evaluation, noisy | success rate | Improved |
Closest papers by meaning
- Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning (ICLR 2025 · similarity 0.86)
- Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning (NeurIPS 2026 · similarity 0.85)
- Confounding Robust Deep Reinforcement Learning: A Causal Approach (NeurIPS 2025 · similarity 0.84)
- Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning (ICLR 2025 · similarity 0.84)
- DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization (NeurIPS 2025 · similarity 0.84)
- DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors (AAAI 2026 · similarity 0.84)
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.
