Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/NothingThrough/LFIRL
Terminology
Sources
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
- Imitation Learning via Off-Policy Distribution Matching
- Hybrid Inverse Reinforcement Learning
- Goal-Conditioned Imitation Learning using Score-based Diffusion Policies
- Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks
- Sobolev Training for Physics Informed Neural Networks
- Generative Adversarial Imitation from Observation
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