pith. sign in

DART: Noise Injection for Robust Imitation Learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

One approach to Imitation Learning is Behavior Cloning, in which a robot observes a supervisor and infers a control policy. A known problem with this "off-policy" approach is that the robot's errors compound when drifting away from the supervisor's demonstrations. On-policy, techniques alleviate this by iteratively collecting corrective actions for the current robot policy. However, these techniques can be tedious for human supervisors, add significant computation burden, and may visit dangerous states during training. We propose an off-policy approach that injects noise into the supervisor's policy while demonstrating. This forces the supervisor to demonstrate how to recover from errors. We propose a new algorithm, DART (Disturbances for Augmenting Robot Trajectories), that collects demonstrations with injected noise, and optimizes the noise level to approximate the error of the robot's trained policy during data collection. We compare DART with DAgger and Behavior Cloning in two domains: in simulation with an algorithmic supervisor on the MuJoCo tasks (Walker, Humanoid, Hopper, Half-Cheetah) and in physical experiments with human supervisors training a Toyota HSR robot to perform grasping in clutter. For high dimensional tasks like Humanoid, DART can be up to $3x$ faster in computation time and only decreases the supervisor's cumulative reward by $5\%$ during training, whereas DAgger executes policies that have $80\%$ less cumulative reward than the supervisor. On the grasping in clutter task, DART obtains on average a $62\%$ performance increase over Behavior Cloning.

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

Hierarchical Policy Learning via Spectral Decomposition

cs.RO · 2026-06-28 · unverdicted · novelty 6.0

Causal Spectral Policy decomposes actions spectrally into coarse motion from obs/language and conditional fine corrections, outperforming baselines on precision manipulation tasks.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Hierarchical Policy Learning via Spectral Decomposition cs.RO · 2026-06-28 · unverdicted · none · ref 24 · internal anchor

    Causal Spectral Policy decomposes actions spectrally into coarse motion from obs/language and conditional fine corrections, outperforming baselines on precision manipulation tasks.