---
title: "Inter-Task Similarity for Lifelong Reinforcement Learning in Heterogeneous Tasks"
authors:
  - "Sergio A. Serrano"
doi: "10.24963/ijcai.2021/689"
url: "https://ijcai.org/proceedings/2021/689"
pdf: "https://ijcai.org/proceedings/2021/0689.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4915-4916"
track: "Doctoral Consortium"
keywords:
  - "Machine Learning: Reinforcement Learning"
  - "Machine Learning: Transfer, Adaptation, Multi-task Learning"
  - "Machine Learning: Incremental Learning"
  - "Robotics: Learning in Robotics"
---

# Inter-Task Similarity for Lifelong Reinforcement Learning in Heterogeneous Tasks

Sergio A. Serrano

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4915-4916. DOI: [10.24963/ijcai.2021/689](https://doi.org/10.24963/ijcai.2021/689)

## Abstract

Reinforcement learning (RL) is a learning paradigm in which an agent interacts with the environment it inhabits to learn in a trial-and-error way. By letting the agent acquire knowledge from its own experience, RL has been successfully applied to complex domains such as robotics. However, for non-trivial problems, training an RL agent can take very long periods of time. Lifelong machine learning (LML) is a learning setting in which the agent learns to solve tasks sequentially, by leveraging knowledge accumulated from previously solved tasks to learn better/faster in a new one. Most LML works heavily rely on the assumption that tasks are similar to each other. However, this may not be true for some domains with a high degree of task-diversity that could benefit from adopting a lifelong learning approach, e.g., service robotics. Therefore, in this research we will address the problem of learning to solve a sequence of RL heterogeneous tasks (i.e., tasks that differ in their state-action space).