research
∙
05/13/2023
Thompson Sampling for Parameterized Markov Decision Processes with Uninformative Actions
We study parameterized MDPs (PMDPs) in which the key parameters of inter...
share
research
∙
11/11/2022
pyRDDLGym: From RDDL to Gym Environments
We present pyRDDLGym, a Python framework for auto-generation of OpenAI G...
research
∙
06/14/2021
RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation
Planning provides a framework for optimizing sequential decisions in com...
research
∙
07/02/2020
ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning
Resolving the exploration-exploitation trade-off remains a fundamental p...
research
∙
06/10/2020
Bayesian Experience Reuse for Learning from Multiple Demonstrators
Learning from demonstrations (LfD) improves the exploration efficiency o...
research
∙
02/29/2020