pith. sign in

Deep Predictive Policy Training using Reinforcement Learning

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

1 Pith paper citing it
abstract

Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The perception and behavior super-layers force an abstraction of visual and motor data trained with synthetic and simulated training samples, respectively. The policy super-layer is a small sub-network with fewer parameters that maps data in-between the abstracted manifolds. It is trained for each task using methods for policy search reinforcement learning. We demonstrate the suitability of the proposed architecture and learning framework by training predictive policies for skilled object grasping and ball throwing on a PR2 robot. The effectiveness of the method is illustrated by the fact that these tasks are trained using only about 180 real robot attempts with qualitative terminal rewards.

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

clear filters

representative citing papers

FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects

cs.RO · 2026-06-01 · unverdicted · novelty 6.0

FlipItRight decomposes pose-targeted throw-flip into object-level and robot-level planners with explicit release states and constant-velocity swings, achieving 90% success across 120 real-robot trials on diverse objects without learned models or data collection.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects cs.RO · 2026-06-01 · unverdicted · none · ref 16 · internal anchor

    FlipItRight decomposes pose-targeted throw-flip into object-level and robot-level planners with explicit release states and constant-velocity swings, achieving 90% success across 120 real-robot trials on diverse objects without learned models or data collection.