OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Properly Acting under Partial Observability with Action Feasibility Constraints

Ponzoni Carvalho Chanel, Caroline and Teichteil-Königsbuch, Florent Properly Acting under Partial Observability with Action Feasibility Constraints. (2013) In: European Conference on Machine Learning, 23 September 2013 - 27 September 2013 (Prague, Czech Republic).

(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://link.springer.com/chapter/10.1007%2F978-3-642-40988-2_10


We introduce Action-Constrained Partially Observable Markov Decision Process (AC-POMDP), which arose from studying critical robotic applications with damaging actions. AC-POMDPs restrict the optimized policy to only apply feasible actions: each action is feasible in a subset of the state space, and the agent can observe the set of applicable actions in the current hidden state, in addition to standard observations. We present optimality equations for AC-POMDPs, which imply to operate on alpha-vectors defined over many different belief subspaces. We propose an algorithm named PreCondition Value Iteration (PCVI), which fully exploits this specific property of AC-POMDPs about alpha-vectors. We also designed a relaxed version of PCVI whose complexity is exponentially smaller than PCVI. Experimental results on POMDP robotic benchmarks with action feasibility constraints exhibit the benefits of explicitly exploiting the semantic richness of action- easibility observations in AC-POMDPs over equivalent but unstructured POMDPs.

Item Type:Conference or Workshop Item (Paper)
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE)
French research institutions > Office National d'Etudes et Recherches Aérospatiales - ONERA (FRANCE)
Laboratory name:
Deposited On:14 Oct 2013 09:41

Repository Staff Only: item control page