← Back to papers

2024 UAI UAI 2024

Bootstrap Your Conversions: Thompson Sampling for Partially Observable Delayed Rewards

Authors

Marco Gigli , Fabio Stella

Related papers

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling 2024

Inference in Probabilistic Answer Set Programs with Imprecise Probabilities via Optimization 2024

Differentially Private No-regret Exploration in Adversarial Markov Decision Processes 2024

Linearly Constrained Gaussian Processes are SkewGPs: application to Monotonic Preference Learning and Desirability 2024

Adaptive Time-Stepping Schedules for Diffusion Models 2024