Exact Distinguishability in Non-Markovian Decision Processes
cs.LG, cs.AI, stat.ML
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/Kcbir/pec
Terminology
Sources
- Tractable Offline Learning of Regular Decision Processes
- Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning
- Bayesian Exploration Networks
- Active Automata Learning with Advice
- Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes
- Bayesian Active Learning for Classification and Preference Learning
- Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
- Exact test for Markov order
- Online Learning of Non-Markovian Reward Models
- Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference
- L*-Based Learning of Markov Decision Processes (Extended Version)
- Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards
- DeepDFA: Automata Learning through Neural Probabilistic Relaxations
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