Reachability-Aware Diffusion Policy Optimization
cs.LG, cs.RO
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Constrained Policy Optimization
- Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances
- $\lambda$-Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
- A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
- Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
- Denoising Diffusion Probabilistic Models
- Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- Verifiable Safety Q-Filters via Hamilton-Jacobi Reachability and Multiplicative Q-Networks
- Safe Offline Reinforcement Learning with Real-Time Budget Constraints
- Constrained Variational Policy Optimization for Safe Reinforcement Learning
- Efficient Online Reinforcement Learning for Diffusion Policy
- Diffusion Policy Policy Optimization
- Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
- Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
- Reward Constrained Policy Optimization
- Policy Representation via Diffusion Probability Model for Reinforcement Learning
- Projection-Based Constrained Policy Optimization
- Reachability Constrained Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks