Research output

  1. Continuous state and action Q-learning framework applied to quadrotor UAV control

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

  2. Safe Exploration Algorithms for Reinforcement Learning Controllers

    Research output: Contribution to journalArticleScientificpeer-review

  3. The Actor-Judge Method: Safe state exploration for Hierarchical Reinforcement Learning Controllers

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

View all (12) »

ID: 195491