In this work we present an empirical study where we demonstrate the possibility of developing an artificial agent that is capable to autonomously explore an experimental scenario. During the exploration, the agent is able to discover and learn interesting options allowing to interact with the environment without any assigned task, and then abstract and re-use the acquired knowledge to solve the assigned tasks. We test the system in the so-called Treasure Game domain described in the recent literature and we empirically demonstrate that the discovered options can be abstracted in an probabilistic symbolic planning model (using the PPDDL language), which allowed the agent to generate symbolic plans to achieve extrinsic goals.
Gabriele, S., Davide, Z., Cialdea, M., Angelo, O., Riccardo, R., Vieri Giuliano Santucci, (2022). Option Discovery for Autonomous Generation of Symbolic Knowledge. In AIxIA 2021 - Advances in Artificial Intelligence, 20th International Conference of the Italian Association for Artificial Intelligence. Springer.
Option Discovery for Autonomous Generation of Symbolic Knowledge
Marta Cialdea Mayer;
2022-01-01
Abstract
In this work we present an empirical study where we demonstrate the possibility of developing an artificial agent that is capable to autonomously explore an experimental scenario. During the exploration, the agent is able to discover and learn interesting options allowing to interact with the environment without any assigned task, and then abstract and re-use the acquired knowledge to solve the assigned tasks. We test the system in the so-called Treasure Game domain described in the recent literature and we empirically demonstrate that the discovered options can be abstracted in an probabilistic symbolic planning model (using the PPDDL language), which allowed the agent to generate symbolic plans to achieve extrinsic goals.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.