Ashwin Ram

TIST Journal 2012 Journal Article

An Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration

• Xiaoqin Shelley Zhang
• Bhavesh Shrestha
• Sungwook Yoon
• Subbarao Kambhampati
• Phillip DiBona
• Jinhong K. Guo
• Daniel McFarlane
• Martin O. Hofmann

We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

IJCAI Conference 2009 Conference Paper

• Jainarayan Radhakrishnan
• Santiago Ontañón
• Ashwin Ram

Goal Driven Learning (GDL) focuses on systems that determine by themselves what has to be learnt and how to learn it. Typically GDL systems use meta-reasoning capabilities over a base reasoner, identifying learning goals and devising strategies. In this paper we present a novel GDL technique to deal with complex AI systems where the metareasoning module has to analyze the reasoning trace of multiple components with potentially different learning paradigms. Our approach works by distributing the generation of learning strategies among the different modules instead of centralizing it in the meta-reasoner. We implemented our technique in the GILA system, that works in the airspace task orders domain, showing an increase in performance.

IJCAI Conference 2007 Conference Paper

• Peng Zang
• Manish Mehta
• Michael Mateas
• Ashwin Ram

Typically, autonomous believable agents are implemented using static, hand-authored reactive behaviors or scripts. This hand-authoring allows designers to craft expressive behavior for characters, but can lead to excessive authorial burden, as well as result in characters that are brittle to changing world dynamics. In this paper, we present an approach for the runtime adaptation of reactive behaviors for autonomous believable characters. Extending transformational planning, our system allows autonomous characters to monitor and reason about their behavior execution and to use this reasoning to dynamically rewrite their behaviors. In our evaluation, we transplant two characters in a sample tag game from the original world they were written for into a different one, resulting in behavior that violates the author intended personality. The reasoning layer successfully adapts the character's behaviors so as to bring its long-term behavior back into agreement with its personality.

IJCAI Conference 2007 Conference Paper

• Manu Sharma
• Michael Holmes
• Juan Santamaria
• Arya Irani
• Charles Isbell
• Ashwin Ram

The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered architecture named CAse-Based Reinforcement Learner (CARL). It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to achieve transfer while playing against the Game AI across a variety of scenarios in MadRTS(TM), a commercial Real Time Strategy game. Our experiments demonstrate that CARL not only performs well on individual tasks but also exhibits significant performance gains when allowed to transfer knowledge from previous tasks.

AIJ Journal 1999 Journal Article

Introspective multistrategy learning: On the construction of learning strategies

• Michael T. Cox
• Ashwin Ram

A central problem in multistrategy learning systems is the selection and sequencing of machine learning algorithms for particular situations. This is typically done by the system designer who analyzes the learning task and implements the appropriate algorithm or sequence of algorithms for that task. We propose a solution to this problem which enables an AI system with a library of machine learning algorithms to select and sequence appropriate algorithms autonomously. Furthermore, instead of relying on the system designer or user to provide a learning goal or target concept to the learning system, our method enables the system to determine its learning goals based on analysis of its successes and failures at the performance task. The method involves three steps: Given a performance failure, the learner examines a trace of its reasoning prior to the failure to diagnose what went wrong (blame assignment); given the resultant explanation of the reasoning failure, the learner posts explicitly represented learning goals to change its background knowledge (deciding what to learn); and given a set of learning goals, the learner uses nonlinear planning techniques to assemble a sequence of machine learning algorithms, represented as planning operators, to achieve the learning goals (learning-strategy construction). In support of these operations, we define the types of reasoning failures, a taxonomy of failure causes, a second-order formalism to represent reasoning traces, a taxonomy of learning goals that specify desired change to the background knowledge of a system, and a declarative task-formalism representation of learning algorithms. We present the Meta-AQUA system, an implemented multistrategy learner that operates in the domain of story understanding. Extensive empirical evaluations of Meta-AQUA show that it performs significantly better in a deliberative, planful mode than in a reflexive mode in which learning goals are ablated and, furthermore, that the arbitrary ordering of learning algorithms can lead to worse performance than no learning at all. We conclude that explicit representation and sequencing of learning goals is necessary for avoiding negative interactions between learning algorithms that can lead to less effective learning.

AIJ Journal 1995 Journal Article

Understanding the Creative Mind: a review of Margaret Boden's creative mind

• Ashwin Ram
• Linda Wills
• Eric Domeshek
• Nancy Nersessian
• Janet Kolodner

AAAI Conference 1987 Conference Paper

AQUA: Asking Questions and Understanding Answers

• Ashwin Ram

Story understanding programs are often designed to answer questions to demonstrate that they have adequately understood a story (e.g., [Leh78]). In contrast, we claim that asking questions is central to understanding. Reading a story involves the generation of questions, which in turn focus the understander on the relevant aspects of the story as it reads further. We are interested in the kinds of questions that people ask as they read. In this paper, we talk about the origin of these questions in the basic cycle of understanding, and their effect on processing. We present an understanding algorithm based on our theory of questions, which we have implemented in a computer program called AQUA (Asking Questions and Understanding Answers).