More Like this

1. An approximate dynamic programming approach to community recovery management

   Nozhati, S.; Ellingwood, B. R.; Mahmoud, H.; Sarkale, Y.; Chong, E. K.; Rosenheim, N. (May 2018, 2018 Engineering Mechanics Institute Conference (EMI))

   The functioning of interdependent civil infrastructure systems in the aftermath of a disruptive event is critical to the performance and vitality of any modern urban community. Post-event stressors and chaotic circumstances, time limitations, and complexities in the community recovery process highlight the necessity for a comprehensive decision-making framework at the community-level for post-event recovery management. Such a framework must be able to handle large-scale scheduling and decision processes, which involve difficult control problems with large combinatorial decision spaces. This study utilizes approximate dynamic programming algorithms along with heuristics for the identification of optimal community recovery actions following the occurrence of an extreme earthquake event. The proposed approach addresses the curse of dimensionality in its analysis and management of multi-state, large-scale infrastructure systems. Furthermore, the proposed approach can consider the cur-rent recovery policies of responsible public and private entities within the community and shows how their performance might be improved. A testbed community coarsely modeled after Gilroy, California, is utilized as an illustrative example. While the illustration provides optimal policies for the Electrical Power Network serving Gilroy following a severe earthquake, preliminary work shows that the methodology is computationally well suited to other infrastructure systems and hazards. 

   more » « less
2. An approximate dynamic programming approach to community recovery management

   Nozhati, S.; Ellingwood, B. R.; Mahmoud, H.; Sarkale, Y.; Chong, E. K.; Rosenheim, N. (May 2018, 2018 Engineering Mechanics Institute Conference (EMI))

   The functioning of interdependent civil infrastructure systems in the aftermath of a disruptive event is critical to the performance and vitality of any modern urban community. Post-event stressors and chaotic circumstances, time limitations, and complexities in the community recovery process highlight the necessity for a comprehensive decision-making framework at the community-level for post-event recovery management. Such a framework must be able to handle large-scale scheduling and decision processes, which involve difficult control problems with large combinatorial decision spaces. This study utilizes approximate dynamic programming algorithms along with heuristics for the identification of optimal community recovery actions following the occurrence of an extreme earthquake event. The proposed approach addresses the curse of dimensionality in its analysis and management of multi-state, large-scale infrastructure systems. Furthermore, the proposed approach can consider the cur-rent recovery policies of responsible public and private entities within the community and shows how their performance might be improved. A testbed community coarsely modeled after Gilroy, California, is utilized as an illustrative example. While the illustration provides optimal policies for the Electrical Power Network serving Gilroy following a severe earthquake, preliminary work shows that the methodology is computationally well suited to other infrastructure systems and hazards. 

   more » « less
3. Deontically Constrained Policy Improvement in Reinforcement Learning Agents

   Makarova, Alena; Abbas, Houssam (July 2025, College Publications)

   vanBerkel, Kees; Ciabattoni, Agata; Horty, John (Ed.)

   Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures nondeterminism, probabilistic uncertainty, and an explicit model of action. A Reinforcement Learning (RL) agent learns to act in an MDP by maximizing a utility function. This paper considers the problem of learning a decision policy that maximizes utility subject to satisfying a constraint expressed in deontic logic. In this setup, the utility captures the agent’s mission - such as going quickly from A to B. The deontic formula represents (ethical, social, situational) constraints on how the agent might achieve its mission by prohibiting classes of behaviors. We use the logic of Expected Act Utilitarianism, a probabilistic stit logic that can be interpreted over controlled MDPs. We develop a variation on policy improvement, and show that it reaches a constrained local maximum of the mission utility. Given that in stit logic, an agent’s duty is derived from value maximization, this can be seen as a way of acting to simultaneously maximize two value functions, one of which is implicit, in a bi-level structure. We illustrate these results with experiments on sample MDPs. 

   more » « less
4. Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language

   https://doi.org/10.1017/S1471068419000371  

   WANG, YI; ZHANG, SHIQI; LEE, JOOHYUNG (September 2019, Theory and Practice of Logic Programming)

   Abstract To be responsive to dynamically changing real-world environments, an intelligent agent needs to perform complex sequential decision-making tasks that are often guided by commonsense knowledge. The previous work on this line of research led to the framework called interleaved commonsense reasoning and probabilistic planning (i corpp ), which used P-log for representing commmonsense knowledge and Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs) for planning under uncertainty. A main limitation of i corpp is that its implementation requires non-trivial engineering efforts to bridge the commonsense reasoning and probabilistic planning formalisms. In this paper, we present a unified framework to integrate i corpp ’s reasoning and planning components. In particular, we extend probabilistic action language pBC + to express utility, belief states, and observation as in POMDP models. Inheriting the advantages of action languages, the new action language provides an elaboration tolerant representation of POMDP that reflects commonsense knowledge. The idea led to the design of the system pbcplus2pomdp , which compiles a pBC + action description into a POMDP model that can be directly processed by off-the-shelf POMDP solvers to compute an optimal policy of the pBC + action description. Our experiments show that it retains the advantages of i corpp while avoiding the manual efforts in bridging the commonsense reasoner and the probabilistic planner. 

   more » « less
5. Hindsight learning for MDPs with exogenous inputs

   Sinclair, Sean_R; Frujeri, Felipe; Cheng, Ching-An; Marshall, Luke; Barbalho, Hugo; Li, Jingling; Neville, Jennifer; Menache, Ishai; Swaminathan, Adith (July 2023, Proceedings of Machine Learning Research)

   Many resource management problems require sequential decision-making under uncertainty, where the only uncertainty affecting the decision outcomes are exogenous variables outside the control of the decision-maker. We model these problems as Exo-MDPs (Markov Decision Processes with Exogenous Inputs) and design a class of data-efficient algorithms for them termed Hindsight Learning (HL). Our HL algorithms achieve data efficiency by leveraging a key insight: having samples of the exogenous variables, past decisions can be revisited in hindsight to infer counterfactual consequences that can accelerate policy improvements. We compare HL against classic baselines in the multi-secretary and airline revenue management problems. We also scale our algorithms to a business-critical cloud resource management problem – allocating Virtual Machines (VMs) to physical machines, and simulate their performance with real datasets from a large public cloud provider. We find that HL algorithms outperform domain-specific heuristics, as well as state-of-the-art reinforcement learning methods. 

   more » « less