A Compression-Inspired Framework for Macro Discovery
Autor: | Garcia, Francisco M., da Silva, Bruno C., Thomas, Philip S. |
---|---|
Rok vydání: | 2017 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Robotics Artificial Intelligence (cs.AI) Computer Science - Artificial Intelligence FOS: Electrical engineering electronic engineering information engineering Computer Science - Systems and Control Systems and Control (eess.SY) Robotics (cs.RO) |
DOI: | 10.48550/arxiv.1711.09048 |
Popis: | In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but related, tasks. One way of exploiting this experience is by identifying recurrent patterns in trajectories obtained from well-performing policies. We propose a three-step framework in which an agent 1) generates a set of candidate open-loop macros by compressing trajectories drawn from near-optimal policies; 2) evaluates the value of each macro; and 3) selects a maximally diverse subset of macros that spans the space of policies typically required for solving the set of related tasks. Our experiments show that extending the original primitive action-set of the agent with the identified macros allows it to more rapidly learn an optimal policy in unseen, but similar MDPs. Comment: Accepted as Extended Abstract, AAMAS, 2019 |
Databáze: | OpenAIRE |
Externí odkaz: |