Search Results for author:
Found 47 papers, 15 papers with code
Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility
The Ride-Pool Matching Problem (RMP) is central to on-demand ride-pooling services, where vehicles must be matched with multiple requests while adhering to service constraints such as pickup delays, detour limits, and vehicle capacity.
On Generalization Across Environments In Multi-Objective Reinforcement Learning
Despite recent advances, existing MORL literature has narrowly focused on performance within static environments, neglecting the importance of generalizing across diverse settings.
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
Unsupervised Environment Design (UED) formalizes the problem of autocurricula through interactive training between a teacher agent and a student agent.
On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering.
Offline Safe Reinforcement Learning Using Trajectory Classification
In this paper, we propose to learn a policy that generates desirable trajectories and avoids undesirable trajectories.
IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health
To address this shortcoming, this paper is the first to present the use of inverse reinforcement learning (IRL) to learn desired rewards for RMABs, and we demonstrate improved outcomes in a maternal and child health telehealth program.
Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs
In this paper, we aim to take this problem and overcome limitations of requiring significant high-quality human data.
UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations
We address the problem of offline learning a policy that avoids undesirable demonstrations.
Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
However, IBL relies on simple fixed form functions to capture the mapping from past situations to current decisions.
Preserving the Privacy of Reward Functions in MDPs through Deception
Experiments on multiple benchmark problems show that our approach outperforms previous methods in preserving reward function privacy.
Safety through feedback in Constrained RL
To address these questions, we introduce \textit{novelty-based sampling} that selectively involves the evaluator only when the the agent encounters a \textit{novel} trajectory.
EduQate: Generating Adaptive Curricula through RMABs in Education Settings
There has been significant interest in the development of personalized and adaptive educational tools that cater to a student's individual learning progress.
Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning
To address this challenge, we propose the Maximum Diversity Fine-Tuning (MDFT) strategy to improve the sample efficiency of fine-tuning in the planning domain.
Bootstrapping Language Models with DPO Implicit Rewards
In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM.
Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios.
Imitating Cost-Constrained Behaviors in Reinforcement Learning
Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by observing the behavior of an expert.
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
In this paper, we propose an offline IL approach that leverages the larger set of sub-optimal demonstrations while effectively mimicking expert trajectories.
Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning
In an exhaustive set of experiments, we demonstrate that our approach is able to outperform top benchmark approaches for solving Constrained RL problems, with respect to expected cost, CVaR cost, or even unknown cost constraints.
Training Reinforcement Learning Agents and Humans With Difficulty-Conditioned Generators
We adapt Parameterized Environment Response Model (PERM), a method for training both Reinforcement Learning (RL) Agents and human learners in parameterized environments by directly modeling difficulty and ability.
Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
Many problems in Reinforcement Learning (RL) seek an optimal policy with large discrete multidimensional yet unordered action spaces; these include problems in randomized allocation of resources such as placements of multiple security resources and emergency response units, etc.
Enhancing the Hierarchical Environment Design via Generative Trajectory Modeling
Unsupervised Environment Design (UED) is a paradigm for automatically generating a curriculum of training environments, enabling agents trained in these environments to develop general capabilities, i. e., achieving good zero-shot transfer performance.
Transferable Curricula through Difficulty Conditioned Generators
In this paper, we introduce a method named Parameterized Environment Response Model (PERM) that shows promising results in training RL agents in parameterized environments.
Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning
Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks.
Future Aware Pricing and Matching for Sustainable On-demand Ride Pooling
Traditionally, both these challenges have been studied individually and using myopic approaches (considering only current requests), without considering the impact of current matching on addressing future requests.
Regret-Based Defense in Adversarial Reinforcement Learning
We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.
Diversity Induced Environment Design via Self-Play
In this paper, we aim to introduce diversity in the Unsupervised Environment Design (UED) framework.
Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties
Constrained Reinforcement Learning has been employed to enforce safety constraints on policy through the use of expected cost constraints.
Generalization through Diversity: Improving Unsupervised Environment Design
Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e. g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board).
Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization
In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e. g., aggregation systems such as Uber, Deliveroo).
Towards Soft Fairness in Restless Multi-Armed Bandits
To avoid starvation in the executed interventions across individuals/regions/communities, we first provide a soft fairness constraint and then provide an approach to enforce the soft fairness constraint in RMABs.
Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits
In this paper, we are interested in ensuring that RMAB decision making is also fair to different arms while maximizing expected value.
Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling
Owing to the benefits for customers (lower prices), drivers (higher revenues), aggregation companies (higher revenues) and the environment (fewer vehicles), on-demand ride pooling (e. g., Uber pool, Grab Share) has become quite popular.
Facilitating human-wildlife cohabitation through conflict prediction
With increasing world population and expanded use of forests as cohabited regions, interactions and conflicts with wildlife are increasing, leading to large-scale loss of lives (animal and human) and livelihoods (economic).
Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health
Our second major contribution is evaluation of our RMAB system in collaboration with an NGO, via a real-world service quality improvement study.
CLAIM: Curriculum Learning Policy for Influence Maximization in Unknown Social Networks
Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information.
Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare
In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks.
Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100, 000 live births.
Competitive Ratios for Online Multi-capacity Ridesharing
The desired matching between resources and request groups is constrained by the edges between requests and request groups in this tripartite graph (i. e., a request can be part of at most one request group in the final assignment).
Zone pAth Construction (ZAC) based Approaches for Effective Real-Time Ridesharing
This challenge has been addressed in existing work by: (i) generating as many relevant feasible (with respect to the available delay for customers) combinations of requests as possible in real-time; and then (ii) optimizing assignment of the feasible request combinations to vehicles.
Value Variance Minimization for Learning Approximate Equilibrium in Aggregation Systems
For effective matching of resources (e. g., taxis, food, bikes, shopping items) to customer demand, aggregation systems have been extremely successful.
On Solving Cooperative MARL Problems with a Few Good Experiences
Unfortunately, neither of these approaches (or their extensions) are able to address the problem of sparse good experiences effectively.
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).
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
This is because even a myopic assignment in ride-pooling involves considering what combinations of passenger requests that can be assigned to vehicles, which adds a layer of combinatorial complexity to the ToD problem.
TuSeRACT: Turn-Sample-Based Real-Time Traffic Signal Control
To ensure real-time responsiveness in the presence of turn-induced uncertainty, SURTRAC computes schedules which minimize the delay for the expected turn movements as opposed to minimizing the expected delay under turn-induced uncertainty.
Resource Constrained Deep Reinforcement Learning
However, existing Deep RL methods are unable to handle combinatorial action spaces and constraints on allocation of resources.
Entropy based Independent Learning in Anonymous Multi-Agent Settings
A key characteristic of the domains of interest is that the interactions between individuals are anonymous, i. e., the outcome of an interaction (competing for demand) is dependent only on the number and not on the identity of the agents.
Regret based Robust Solutions for Uncertain Markov Decision Processes
Most robust optimization approaches for these problems have focussed on the computation of {\em maximin} policies which maximize the value corresponding to the worst realization of the uncertainty.
