Research map / Reinforcement learning / Offline RL
Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning
Xuemin Hu, Shen Li, Yingfen Xu, Bo Tang, Long Chen
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 diffusion policy instead of Gaussian (VAE) policy (ablation) | DMGDP · D4RL Gym-MuJoCo mean | normalized score: 86.06 -> 94.28 | Improved |
| use diffusion policy instead of Gaussian policy (ablation) | DMGDP · D4RL Hopper-medium | normalized score: 60.2 -> 101.3 | Improved |
| add discriminator-based policy confidence (ablation) | DMGDP · D4RL 10-task mean | normalized score: 88.83 -> 93.01 | Improved |
| add policy confidence (ablation) | DMGDP · D4RL Antmaze-medium-play | normalized score: 79 -> 85.3 | Improved |
| add policy confidence (ablation) | DMGDP · D4RL Walker2d-medium | normalized score: 89.2 -> 88.7 | No clear effect |
| vary lambda from 0.5 to 8 (ablation) | DMGDP · D4RL Antmaze-medium | success rate | No clear effect |
| use DMGDP instead of D-DICE | DMGDP · D4RL Antmaze-large-play | normalized score: 68.6 -> 62.7 | Hurt |
| use DMGDP instead of DQL | DMGDP · D4RL all-tasks mean | normalized score: 80.6 -> 89.54 | Improved |
Closest papers by meaning
- Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation Learning (AAAI 2025 · similarity 0.90)
- Generative OOD-regularized Model-based Policy Optimization (NeurIPS 2026 · similarity 0.90)
- Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation (ICML 2025 · similarity 0.89)
- Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
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.
