The Strength of Weak Learnability
Machine Learning
A natural semantics for lazy evaluation
POPL '93 Proceedings of the 20th ACM SIGPLAN-SIGACT symposium on Principles of programming languages
Acting optimally in partially observable stochastic domains
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Machine Learning
Robust constrained model predictive control using linear matrix inequalities
Automatica (Journal of IFAC)
Quantitative Stability in Stochastic Programming: The Method of Probability Metrics
Mathematics of Operations Research
PEGASUS: A policy search method for large MDPs and POMDPs
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Dynamic Programming
Generating Scenario Trees for Multistage Decision Problems
Management Science
Tree-Based Batch Mode Reinforcement Learning
The Journal of Machine Learning Research
Stability of Multistage Stochastic Programs
SIAM Journal on Optimization
Confidence level solutions for stochastic programming
Automatica (Journal of IFAC)
Reinforcement learning versus model predictive control: a comparison on a power system problem
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
This paper addresses the problem of solving discrete-time optimal sequential decision making problems having a disturbance space W composed of a finite number of elements. In this context, the problem of finding from an initial state x 0 an optimal decision strategy can be stated as an optimization problem which aims at finding an optimal combination of decisions attached to the nodes of a disturbance tree modeling all possible sequences of disturbances w 0 , w 1 , ..., $w_{T-1} \in W^T$ over the optimization horizon T . A significant drawback of this approach is that the resulting optimization problem has a search space which is the Cartesian product of O (|W | T *** 1) decision spaces U , which makes the approach computationally impractical as soon as the optimization horizon grows, even if W has just a handful of elements. To circumvent this difficulty, we propose to exploit an ensemble of randomly generated incomplete disturbance trees of controlled complexity, to solve their induced optimization problems in parallel, and to combine their predictions at time t = 0 to obtain a (near-)optimal first-stage decision. Because this approach postpones the determination of the decisions for subsequent stages until additional information about the realization of the uncertain process becomes available, we call it lazy . Simulations carried out on a robot corridor navigation problem show that even for small incomplete trees, this approach can lead to near-optimal decisions.