Deep Reinforcement Learning (DRL) is a promising approach in the development of autonomous agents adopted in different contexts, from robotic control to virtual avatars in video games. The present contribution presents an application of DRL to the context of pedestrian simulation: building on previous results, we focus on wayfinding decisions, i.e. the decisions among different alternative trajectories within an annotated (planar) environment comprising rooms and passages, in which the agent might need to reach specific intermediate goals before moving towards a final exit. By employing a curriculum based approach, the learning process guides agents to develop a policy leading to the exploration of the environment to reach a set of intermediate waypoints and the final movement target, irrespectively of the specific map of the environment. We discuss the adopted approach, the achieved results, and we discuss potential steps towards improving the explainability of the training process by means of formalization of scenarios included in the curriculum, and their intended training goals.
Vizzari, G., Briola, D., Cecconello, T. (2023). Curriculum–Based Reinforcement Learning for Pedestrian Simulation: Towards an Explainable Training Process. In Proceedings of the 24th Workshop "From Objects to Agents" (pp.32-48). CEUR-WS.
Curriculum–Based Reinforcement Learning for Pedestrian Simulation: Towards an Explainable Training Process
Vizzari G.Primo
;Briola D.Secondo
;Cecconello T.Ultimo
2023
Abstract
Deep Reinforcement Learning (DRL) is a promising approach in the development of autonomous agents adopted in different contexts, from robotic control to virtual avatars in video games. The present contribution presents an application of DRL to the context of pedestrian simulation: building on previous results, we focus on wayfinding decisions, i.e. the decisions among different alternative trajectories within an annotated (planar) environment comprising rooms and passages, in which the agent might need to reach specific intermediate goals before moving towards a final exit. By employing a curriculum based approach, the learning process guides agents to develop a policy leading to the exploration of the environment to reach a set of intermediate waypoints and the final movement target, irrespectively of the specific map of the environment. We discuss the adopted approach, the achieved results, and we discuss potential steps towards improving the explainability of the training process by means of formalization of scenarios included in the curriculum, and their intended training goals.File | Dimensione | Formato | |
---|---|---|---|
Vizzari-2023-WOA-VoR.pdf
accesso aperto
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Creative Commons
Dimensione
3.5 MB
Formato
Adobe PDF
|
3.5 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.