Toward Sophisticated Agent-based Universes - Statements to Introduce Some Realistic Features into Classic AI/RL Problems

Filipo Studzinski Perotto (1)

1 IRIT - Institut de recherche en informatique de Toulouse

In this paper we analyze some common simplifications present in the traditional AI / RL problems. We argue that only facing particular conditions, often avoided in the classic statements, will allow the overcoming of the actual limits of the science, and the achievement of new advances in respect to realistic scenarios. This paper does not propose any paradigmatic revolution, but it presents a compilation of several different elements proposed more or less separately in recent AI research, unifying them by some theoretical reflections, experiments and computational solutions. Broadly, we are talking about scenarios where AI needs to deal with true situatedness agency, providing some kind of anticipatory learning mechanism to the agent in order to allow it to adapt itself to the environment.

Mots clés: Factored Partially Observable Markov Decision Process (FPOMDP); Model-Based Reinforcement Learning; Agency theory; Constructivist learning mechanisms; Anticipatory learning; Model-based reinforcement learning; Factored Partially Observable Markov Decision Process (FPOMDP); Constructivist Learning Mechanisms; Anticipatory Learning

Domaines: Intelligence artificielle [cs.AI]

Filipo Studzinski Perotto. Toward Sophisticated Agent-based Universes - Statements to Introduce Some Realistic Features into Classic AI/RL Problems. ICAART 2012 - Proceedings of the 4th International Conference on Agents and Artificial Intelligence, Vilamoura, Algarve, Portugal, 6-8 February, 2012, 2012, Berlin/Heidelberg, Georgia. pp.433--438, ⟨10.5220/0003835604330438⟩. ⟨hal-01762255⟩