Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems
math.OC, cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Sources
- Continuous Policy and Value Iteration for Relaxed Stochastic Control Problems and Its Convergence
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces
- Mirror Descent for Stochastic Control Problems with Measure-valued Controls
- Diffusion Policy Policy Optimization
- Regret of exploratory policy improvement and q-learning
- A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee
- Solving Time-Continuous Stochastic Optimal Control Problems: Algorithm Design and Convergence Analysis of Actor-Critic Flow
- Diffusion Models for Reinforcement Learning: A Survey
Related papers
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
- Incremental Learning in Mirror Flows
- Second-Order Optimization with Asynchronous Curvature
- Online Control via Counterfactual Tracking
- Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability