cs.RONov 7, 2026

Deploying Physically and Epistemically Compliant Agents by Distilling Belief-Space Task and Motion Planners

Authors: Phillip J. K. Christoffersen, Rachel Ma, Patrick Barragán, Dylan Hadfield-Menell

Organizations: MIT CSAIL.

Abstract

In this work, we train agents to act under uncertainty according to specified, belief-dependent rules. Deep reinforcement learning (RL) can in theory train agents to follow rules if encoded into well-designed rewards, but in practice, RL fails to perfectly optimize these rewards, leading to ineffective or noncompliant agent behavior. Belief-space planners by construction produce behavior in line with developer specification, but require hand-programming online planners and belief-state estimators, adding significant engineering complexity at scale. We combine the two: we plan offline to generate a dataset of sample trajectories and then distill the plans into a policy that acts on raw observations. We propose two changes to planner distillation that address problems specific to history-based policies: Dual Averaging, a loss that combines per-timestep predictive loss and average loss on task changes, and ρρ-Optimal Reinforcement, a feedback mechanism that reinforces the policy's own successful rollouts when these are near-optimal. We provide a sufficient condition under which static search problems with noiseless observation models is complete, and show that maximum-likelihood-observation planning implies this condition in static search with continuous beliefs. We create a challenging new domain, Scavenger, where an agent needs to gain information in order to succeed. We evaluate our distilled policy in two versions of Scavenger, one where information is provided visually and one where it is provided as a command in natural language. In either case, the learned policy attains a success rate above 90% in Scavenger, compared with at most 5% for RL. We also find that distilled planners transfer with greater than 60% success to following unseen and intentionally vague commands and greater than 75% success to following floorplans larger than those seen in training.

Figures & tables

Explore similar work

CardsList
  1. Learning to Search and Searching to Learn for Generalization in Planning

    May 25, 2026Michael Aichmüller, Yannik Hesse, Hector GeffnerReinforcement LearningGeneralization in RL

  2. State Trace Rationale As Auxiliary Task in Reinforcement Learning

    Sep 29, 2026Muhammad U. Nasir, Alex Vogt, Steven D. James +1Reinforcement LearningRepresentation Learning for RL

  3. What Can a VLA Learn from the Agent That Calls It? Task-Level Experience Distillation for Embodied Navigation

    Nov 12, 2026Jinze Tao, Yuxiao Han, Kangkang Dong +4Vision-Language NavigationVision-Language-Action Models