• Publications
  • Influence
A polynomial algorithm for decentralized Markov decision processes with temporal constraints
TLDR
This paper presents a class of Decentralized MDPs, OC-DEC-MDP, that can handle temporal and precedence constraints, and introduces an opportunity cost to allow the agents to coordinate. Expand
Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs
TLDR
A heuristic search method, namely Point Based Incremental Pruning (PBIP), which is able to distinguish policies with different heuristic estimates, is suggested, which permits us to reduce clearly the amount of computation required by the exhaustive backup of DEC-POMDP. Expand
Coordinated Multi-Robot Exploration Under Communication Constraints Using Decentralized Markov Decision Processes
TLDR
This paper extends the DVF methodology to address full local observability, limited share of information and communication breaks and applies it in a real-world application consisting of multi-robot exploration where each robot computes locally a strategy that minimizes the interactions between the robots and maximizes the space coverage of the team even under communication constraints. Expand
Decision-Theoretic Control of Planetary Rovers
TLDR
Two decision-theoretic approaches to maximize the productivity of planetary rovers are described: one based on adaptive planning and the other on hierarchical reinforcement learning. Expand
Multi-Objective MDPs with Conditional Lexicographic Reward Preferences
TLDR
A rich model called Lexicographic MDP (LMDP) and a corresponding planning algorithm called LVI that generalize previous work by allowing for conditional lexicographic preferences with slack are introduced and the convergence characteristics of LVI are analyzed. Expand
Partially Observable Markov Decision Process for Managing Robot Collaboration with Human
TLDR
A new framework for controlling a robot collaborating with a human to accomplish a common mission and some preliminary results of solving the POMDP model with standard optimal algorithms as a base work to compare with state-of-the-art and future-work approximate algorithms. Expand
Distributed value functions for multi-robot exploration
TLDR
This paper addresses the problem of exploring an unknown area with a team of autonomous robots using decentralized decision making techniques as a set of individual Decentralized Markov Decision Process (Dec-MDPs), where interactions between MDPs are considered in a distributed value function. Expand
Humans-Robots Sliding Collaboration Control in Complex Environments with Adjustable Autonomy
TLDR
This paper introduces a model called HHP-MDP (Human Help Provider MDP), that aims at handling the difficult situations met by the agents by using the human's help, and describes how a controller can handle different requests and assign agent requests to the humans by taking into account their previously learned abilities. Expand
Solving efficiently Decentralized MDPs with temporal and resource constraints
TLDR
A new model is presented that allows for large multi-agent decision problems with temporal and precedence constraints to be represented and polynomial algorithms to efficiently solve problems formalized by OC-DEC-MDPs are proposed. Expand
Progressive goal-directed reasoning for real-time AI systems
TLDR
The ability of goal-directed reasoning to address the reactivity and guarantee response time in RT-SOS (Real-Time Society of Specialists) in which asynchronous acquisition, interruptible reasoning, progressive reasoning and adaptive reasoning contribute to meet the real-time requirements. Expand
...
1
2
3
4
5
...