Skip to main content
Search

Phillip J. K. Christoffersen

1 related articles

Subscribe to updates
  1. arXiv

    Distilling belief-space planners into policies: over 90% success in Scavenger, where RL baselines top out at 5%

    In partially observed tasks where an agent must gather information before acting, training the agent directly rarely yields reliable compliance with belief-dependent rules. The approach plans offline with a belief-space task and motion planner in a simulator, then distills those plans into a policy that acts on raw observations, adding a dual-averaging loss and near-optimal reinforcement. In the new Scavenger domain, success exceeds 90% for both the visual-hint and language-hint versions, while reward-engineered RL baselines reach at most 5%.

You’re all caught up