1. 2020
  2. Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics

    Steckelmacher, D., Plisnier, H., Roijers, D. & Nowe, A., 2020, Lecture Notes in Artificial Intelligence: Machine Learning and Knowledge Discovery in Databases (ECML-PKDD proceedings), volume III. Springer, Vol. 11908. 16 p. 48. (Lecture Notes in Artificial Intelligence; vol. 11908).

    Research output: Chapter in Book/Report/Conference proceedingConference paper

  3. 2019
  4. Transfer Reinforcement Learning across Environment Dynamics with Multiple Advisors

    Plisnier, H., Steckelmacher, D., Roijers, D. & Nowe, A., 6 Nov 2019, Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019). CEUR Workshop Proceedings, Vol. 2491. 16 p. 11. (CEUR Workshop Proceedings; vol. 2491, no. 11).

    Research output: Chapter in Book/Report/Conference proceedingConference paper

  5. Transfer Learning Across Simulated Robots With Different Sensors

    Plisnier, H., Steckelmacher, D., Roijers, D. & Nowe, A., 18 Jul 2019. 6 p.

    Research output: Unpublished contribution to conferenceUnpublished paper

  6. The Actor-Advisor: Policy Gradient With Off-Policy Advice

    Plisnier, H., Steckelmacher, D., Roijers, D. & Nowe, A., 7 Feb 2019. 8 p.

    Research output: Unpublished contribution to conferenceUnpublished paper

  7. 2018
  8. Directed Policy Gradient for Safe Reinforcement Learning with Human Advice

    Plisnier, H., Steckelmacher, D., Brys, T., Roijers, D. & Nowe, A., 3 Oct 2018.

    Research output: Unpublished contribution to conferenceUnpublished paper

  9. Directed Policy Gradient for Safe Reinforcement Learning with Human Advice

    Plisnier, H., Steckelmacher, D., Brys, T., Roijers, D. & Nowe, A., 3 Oct 2018.

    Research output: Unpublished contribution to conferencePoster

  10. Off-Policy and Off-Actor Actor-Critic with Bootstrapped Dual Policy Iteration

    Steckelmacher, D., Plisnier, H., Roijers, D. & Nowe, A., 3 Oct 2018. 8 p.

    Research output: Unpublished contribution to conferencePoster

  11. Bootstrapped Dual Policy Iteration

    Steckelmacher, D. & Plisnier, H., 1 Sep 2018

    Research output: Non-textual formSoftware

  12. Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets

    Steckelmacher, D., Roijers, D., Harutyunyan, A., Vrancx, P., Plisnier, H. & Nowe, A., 4 Feb 2018, Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. AAAI Press, p. 4099-4106 8 p. 4099. (AAAI Conference on Artificial Intelligence).

    Research output: Chapter in Book/Report/Conference proceedingConference paper

Previous 1 2 Next

ID: 35142582