Research output

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

    Research output: Unpublished contribution to conferenceUnpublished paperResearch

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

    Research output: Unpublished contribution to conferencePosterResearch

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

    Research output: Unpublished contribution to conferencePosterResearch

View all (6) »

Activities

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

    Activity: Talk or presentationTalk or presentation at a workshop/seminar

  2. Hierarchical Reinforcement Learning for a Robotic Partially Observable Task

    Activity: Talk or presentationTalk or presentation at a conference

View all (2) »

Prizes

  1. BNAIC SKBS Best Demo Award

    Prize: Prize (including medals and awards)

View all (1) »

ID: 35142582