Stochastic Action Prediction for Imitation Learning

• URL: http://arxiv.org/abs/2101.01055v1
• Date: Sat, 26 Dec 2020 08:02:33 GMT
• Title: Stochastic Action Prediction for Imitation Learning
• Authors: Sagar Gubbi Venkatesh and Nihesh Rathod and Shishir Kolathaya and Bharadwaj Amrutur
• Abstract summary: Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. We demonstrate inherentity in demonstrations collected for tasks including line following with a remote-controlled car. We find that accounting for adversariality in the expert data leads to substantial improvement in the success rate of task completion.
• Score: 1.6385815610837169
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. When performing demonstrations, experts are not always consistent and might accomplish the same task in slightly different ways. In this paper, we demonstrate inherent stochasticity in demonstrations collected for tasks including line following with a remote-controlled car and manipulation tasks including reaching, pushing, and picking and placing an object. We model stochasticity in the data distribution using autoregressive action generation, generative adversarial nets, and variational prediction and compare the performance of these approaches. We find that accounting for stochasticity in the expert data leads to substantial improvement in the success rate of task completion.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.