Saved in:
Bibliographic Details
Main Authors: Sahabandu, Dinuka, Ramasubramanian, Bhaskar, Alexiou, Michail, Mertoguno, J. Sukarno, Bushnell, Linda, Poovendran, Radha
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.20466
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916339207110656
author Sahabandu, Dinuka
Ramasubramanian, Bhaskar
Alexiou, Michail
Mertoguno, J. Sukarno
Bushnell, Linda
Poovendran, Radha
author_facet Sahabandu, Dinuka
Ramasubramanian, Bhaskar
Alexiou, Michail
Mertoguno, J. Sukarno
Bushnell, Linda
Poovendran, Radha
contents This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple environments. Unlike traditional methods that require extensive retraining or fine-tuning, our approach integrates existing knowledge, enabling an RL agent to adapt swiftly to new settings without requiring extensive computational resources. Our contributions include development of the Multi-Critic Actor-Critic (MCAC) algorithm, establishing its convergence, and empirical evidence demonstrating its efficacy. Our experimental results show that MCAC significantly outperforms the baseline actor-critic algorithm, achieving up to 22.76x faster autonomy transfer and higher reward accumulation. This advancement underscores the potential of leveraging accumulated knowledge for efficient adaptation in RL applications.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20466
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Method for Fast Autonomy Transfer in Reinforcement Learning
Sahabandu, Dinuka
Ramasubramanian, Bhaskar
Alexiou, Michail
Mertoguno, J. Sukarno
Bushnell, Linda
Poovendran, Radha
Machine Learning
Artificial Intelligence
This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple environments. Unlike traditional methods that require extensive retraining or fine-tuning, our approach integrates existing knowledge, enabling an RL agent to adapt swiftly to new settings without requiring extensive computational resources. Our contributions include development of the Multi-Critic Actor-Critic (MCAC) algorithm, establishing its convergence, and empirical evidence demonstrating its efficacy. Our experimental results show that MCAC significantly outperforms the baseline actor-critic algorithm, achieving up to 22.76x faster autonomy transfer and higher reward accumulation. This advancement underscores the potential of leveraging accumulated knowledge for efficient adaptation in RL applications.
title A Method for Fast Autonomy Transfer in Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.20466