A Convergence Framework for Deep V-Learning: Error Propagation and Sharp Action-Gap Bounds
cs.LG, cs.RO, math.OC
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 37 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Socially Aware Motion Planning with Deep Reinforcement Learning
- Robot Navigation with Entity-Based Collision Avoidance using Deep Reinforcement Learning
- Hybrid Motion Planning with Deep Reinforcement Learning for Mobile Robot Navigation
- What are the Statistical Limits of Offline RL with Linear Function Approximation?
- A Theoretical Analysis of Deep Q-Learning
- Deep Reinforcement Learning with Double Q-learning
- Convergence Results For Q-Learning With Experience Replay
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks