HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm

Kasun Weerakoon, Souradip Chakraborty, Nare Karapetyan, Adarsh Jagan Sathyamoorthy, Amrit Bedi, Dinesh Manocha
Proceedings of The 6th Conference on Robot Learning, PMLR 205:1629-1639, 2023.

Abstract

We present a novel approach to improve the performance of deep reinforcement learning (DRL) based outdoor robot navigation systems. Most, existing DRL methods are based on carefully designed dense reward functions that learn the efficient behavior in an environment. We circumvent this issue by working only with sparse rewards (which are easy to design) and propose a novel adaptive Heavy-Tailed Reinforce algorithm for Outdoor Navigation called HTRON. Our main idea is to utilize heavy-tailed policy parametrizations which implicitly induce exploration in sparse reward settings. We evaluate the performance of HTRON against Reinforce, PPO, and TRPO algorithms in three different outdoor scenarios: goal-reaching, obstacle avoidance, and uneven terrain navigation. We observe average an increase of 34.41% in terms of success rate, a 15.15% decrease in the average time steps taken to reach the goal, and a 24.9% decrease in the elevation cost compared to the navigation policies obtained by the other methods. Further, we demonstrate that our algorithm can be transferred directly into a Clearpath Husky robot to perform outdoor terrain navigation in real-world scenarios.

Cite this Paper


BibTeX
@InProceedings{pmlr-v205-weerakoon23a, title = {HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm}, author = {Weerakoon, Kasun and Chakraborty, Souradip and Karapetyan, Nare and Sathyamoorthy, Adarsh Jagan and Bedi, Amrit and Manocha, Dinesh}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {1629--1639}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/weerakoon23a/weerakoon23a.pdf}, url = {https://proceedings.mlr.press/v205/weerakoon23a.html}, abstract = {We present a novel approach to improve the performance of deep reinforcement learning (DRL) based outdoor robot navigation systems. Most, existing DRL methods are based on carefully designed dense reward functions that learn the efficient behavior in an environment. We circumvent this issue by working only with sparse rewards (which are easy to design) and propose a novel adaptive Heavy-Tailed Reinforce algorithm for Outdoor Navigation called HTRON. Our main idea is to utilize heavy-tailed policy parametrizations which implicitly induce exploration in sparse reward settings. We evaluate the performance of HTRON against Reinforce, PPO, and TRPO algorithms in three different outdoor scenarios: goal-reaching, obstacle avoidance, and uneven terrain navigation. We observe average an increase of 34.41% in terms of success rate, a 15.15% decrease in the average time steps taken to reach the goal, and a 24.9% decrease in the elevation cost compared to the navigation policies obtained by the other methods. Further, we demonstrate that our algorithm can be transferred directly into a Clearpath Husky robot to perform outdoor terrain navigation in real-world scenarios.} }
Endnote
%0 Conference Paper %T HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm %A Kasun Weerakoon %A Souradip Chakraborty %A Nare Karapetyan %A Adarsh Jagan Sathyamoorthy %A Amrit Bedi %A Dinesh Manocha %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-weerakoon23a %I PMLR %P 1629--1639 %U https://proceedings.mlr.press/v205/weerakoon23a.html %V 205 %X We present a novel approach to improve the performance of deep reinforcement learning (DRL) based outdoor robot navigation systems. Most, existing DRL methods are based on carefully designed dense reward functions that learn the efficient behavior in an environment. We circumvent this issue by working only with sparse rewards (which are easy to design) and propose a novel adaptive Heavy-Tailed Reinforce algorithm for Outdoor Navigation called HTRON. Our main idea is to utilize heavy-tailed policy parametrizations which implicitly induce exploration in sparse reward settings. We evaluate the performance of HTRON against Reinforce, PPO, and TRPO algorithms in three different outdoor scenarios: goal-reaching, obstacle avoidance, and uneven terrain navigation. We observe average an increase of 34.41% in terms of success rate, a 15.15% decrease in the average time steps taken to reach the goal, and a 24.9% decrease in the elevation cost compared to the navigation policies obtained by the other methods. Further, we demonstrate that our algorithm can be transferred directly into a Clearpath Husky robot to perform outdoor terrain navigation in real-world scenarios.
APA
Weerakoon, K., Chakraborty, S., Karapetyan, N., Sathyamoorthy, A.J., Bedi, A. & Manocha, D.. (2023). HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:1629-1639 Available from https://proceedings.mlr.press/v205/weerakoon23a.html.

Related Material