Showing papers by "Aditya Grover published in 2015"

A Deep Hybrid Model for Weather Forecasting

Abstract: Weather forecasting is a canonical predictive challenge that has depended primarily on model-based methods. We explore new directions with forecasting weather as a data-intensive challenge that involves inferences across space and time. We study specifically the power of making predictions via a hybrid approach that combines discriminatively trained predictive models with a deep neural network that models the joint statistics of a set of weather-related variables. We show how the base model can be enhanced with spatial interpolation that uses learned long-range spatial dependencies. We also derive an efficient learning and inference procedure that allows for large scale optimization of the model parameters. We evaluate the methods with experiments on real-world meteorological data that highlight the promise of the approach.

ASAP-UCT: abstraction of state-action pairs in UCT

Abstract: Monte-Carlo Tree Search (MCTS) algorithms such as UCT are an attractive online framework for solving planning under uncertainty problems modeled as a Markov Decision Process. However, MCTS search trees are constructed in flat state and action spaces, which can lead to poor policies for large problems. In a separate research thread, domain abstraction techniques compute symmetries to reduce the original MDP. This can lead to significant savings in computation, but these have been predominantly implemented for offline planning. This paper makes two contributions. First, we define the ASAP (Abstraction of State-Action Pairs) framework, which extends and unifies past work on domain abstractions by holistically aggregating both states and state-action pairs - ASAP uncovers a much larger number of symmetries in a given domain. Second, we propose ASAP-UCT, which implements ASAP-style abstractions within a UCT framework combining strengths of online planning with domain abstractions. Experimental evaluation on several benchmark domains shows up to 26% improvement in the quality of policies obtained over existing algorithms.

A Novel Abstraction Framework for Online Planning: Extended Abstract

Abstract: ions are a useful tool for computing policies in large domains modeled as a Markov Decision Process. Prior work in this field is mostly focused on developing different notions for state abstractions. In this paper, we develop a novel framework for abstractions, which unifies prior work and directly exploits symmetry at the state-action pair level, thereby uncovering a much larger number of symmetries in a given domain. We describe the application of abstractions computed through this framework in UCT, a popular MCTS technique for online planning.