Research map / Reinforcement learning / Offline RL
Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning
Mahmoud Selim, Cristina Cipriani, Karl Henrik Johansson
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 |
|---|---|---|---|
| define value on noisy latents via expected clean-action return (NSAC) instead of applying the clean critic directly to noisy latents (DAC) | diffusion actor-critic · AntMaze-large-play-v0 | normalized score: 50.3 -> 77.8 | Improved |
| same change versus DAC | diffusion actor-critic · AntMaze-large-diverse-v0 | normalized score: 55.3 -> 78 | Improved |
| same change versus DAC | diffusion actor-critic · Pen-Cloned-v1 | normalized score: 63.9 -> 84.6 | Improved |
| same change versus DAC | diffusion actor-critic · D4RL locomotion total | normalized score: 836.4 -> 861.7 | Improved |
| same change versus DAC | diffusion actor-critic · OGBench visual (4 tasks) | aggregate success rate: 255.9 -> 271.5 | Improved |
| same change versus DAC | diffusion actor-critic · AntMaze total | normalized score: 275.4 -> 337.2 | Improved |
| use excessively strong guidance strength lambda instead of intermediate values {1,3,10} (ablation) | NSAC · D4RL tasks | learning performance | Hurt |
| increase number of Monte Carlo samples for the noisy-space expectation (ablation) | NSAC · D4RL tasks | learning performance | No clear effect |
| use two Monte Carlo samples instead of more (ablation) | NSAC · training cost | training time: approximately 10% faster than prior diffusion actor-critic | Improved |
| vary pessimism coefficient rho over a broad range (ablation) | NSAC · D4RL tasks | performance | No clear effect |
Closest papers by meaning
- Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning (ICLR 2025 · similarity 0.93)
- Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning (ICML 2025 · similarity 0.91)
- Score Regularized Policy Optimization through Diffusion Behavior (ICLR 2024 · similarity 0.91)
- Prior-Guided Diffusion Planning for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
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.
