Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs
cs.LG, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Optimizing Memory-Bounded Controllers for Decentralized POMDPs
- Scalable Policy-Based RL Algorithms for POMDPs
- Recurrent Natural Policy Gradient for POMDPs
- Stability of the optimal filter in a hidden Markov model with multiplicative noise
- Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
- Partially Observable Markov Decision Processes (POMDPs) and Robotics
- Learning Finite-State Controllers for Partially Observable Environments
- POPGym: Benchmarking Partially Observable Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Mirror Descent Policy Optimization
- Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
- The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis