Search Results for author:
Found 5 papers, 2 papers with code
Information-Theoretic Safe Bayesian Optimization
In this paper, we propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization
Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation (UBE), but the over-approximation may result in inefficient exploration.
Value-Distributional Model-Based Reinforcement Learning
We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the posterior distribution over value functions induced by parameter (epistemic) uncertainty of the Markov decision process.
Model-Based Uncertainty in Value Functions
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning.
Information-Theoretic Safe Exploration with Gaussian Processes
We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint.
