Search Results for author:
Found 20 papers, 6 papers with code
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
To enhance training robustness, RL has adopted techniques from supervised learning, such as ensembles and layer normalization.
Reinforcement Learning for Fine-tuning Text-to-speech Diffusion Models
Recent advancements in generative models have sparked significant interest within the machine learning community.
The Distributional Reward Critic Architecture for Perturbed-Reward Reinforcement Learning
We study reinforcement learning in the presence of an unknown reward perturbation.
Coevolutionary Algorithm for Building Robust Decision Trees under Minimax Regret
It outperformed all competing methods on 13 datasets with adversarial accuracy metrics, and on all 20 considered datasets with minimax regret.
Reflections from the Workshop on AI-Assisted Decision Making for Conservation
In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022.
Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
In this paper, we propose solutions to these issues, avoiding the aforementioned assumptions and utilizing the ML model's features to increase the sample efficiency of learning loss functions.
Normality-Guided Distributional Reinforcement Learning for Continuous Control
Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value distribution, not just the mean.
Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses
Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to perform better on that specific task.
Training Transition Policies via Distribution Matching for Complex Tasks
We introduce transition policies that smoothly connect lower-level policies by producing a distribution of states and actions that matches what is expected by the next policy.
Robust Reinforcement Learning Under Minimax Regret for Green Security
We formulate the problem as a game between the defender and nature who controls the parameter values of the adversarial behavior and design an algorithm MIRROR to find a robust policy.
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
Collapsing Bandits and Their Application to Public Health Intervention
Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable.
Dual-Mandate Patrols: Multi-Armed Bandits for Green Security
Conservation efforts in green security domains to protect wildlife and forests are constrained by the limited availability of defenders (i. e., patrollers), who must patrol vast areas to protect from attackers (e. g., poachers or illegal loggers).
Collapsing Bandits and Their Application to Public Health Interventions
(ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed-form.
Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
Solving optimization problems with unknown parameters often requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values.
AI for Social Impact: Learning and Planning in the Data-to-Deployment Pipeline
With the maturing of AI and multiagent systems research, we have a tremendous opportunity to direct these advances towards addressing complex societal problems.
Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning
To solve the online problem with a hard bound on risk, we formulate it as a Reinforcement Learning (RL) problem with constraints on the action space (hard bound on risk).
End-to-End Game-Focused Learning of Adversary Behavior in Security Games
Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary.
Exploring Strategy-Proofness, Uniqueness, and Pareto Optimality for the Stable Matching Problem with Couples
The Stable Matching Problem with Couples (SMP-C) is a ubiquitous real-world extension of the stable matching problem (SMP) involving complementarities.
