arXiv:2602. 23672v2 Announce Type: replace-cross Abstract: This study proposes a General Bayes framework for policy learning.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2607. 28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback.
arXiv:2606. 19117v1 Announce Type: cross Abstract: Offline policy learning has received growing attention in causal inference.
The paper introduces PreferenceEKF, a sample‑efficient method for active reward learning from human preferences. By framing preference learning as a sequential Bayesian filtering problem, it tracks reward model uncertainty using an extended Kalman filter in a low‑dimensional subspace, avoiding costly posterior inference over the full neural network. Experiments on D4RL and V‑D4RL benchmarks show improved sample efficiency, runtime, scalability, and calibration, with reward models that support competitive offline reinforcement learning policies.
arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.
arXiv:2509. 03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits.
The paper introduces a framework for optimal policy improvement in reinforcement learning, defining it as the best single update under given constraints. It shows that restricting improvement to a subset of states is equivalent to solving an induced Markov Decision Process, linking planning with explicit or implicit models to optimal policy improvement. The authors develop a novel operator for greedification under approximate evaluation, demonstrating empirical gains across several RL algorithms and settings.