ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL
cs.LG, cs.AI, cs.RO
Submitted: 2026-06-02
Updated: 2026-09-25
Terminology
Sources
- Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
- Inversely Learning Transferable Rewards via Abstracted States
- Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
- TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- CoMI-IRL: Contrastive Multi-Intention Inverse 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks