![]() The first investigation contributed two classes of reasoning approaches for arbitrating between diverse types of active learning queries, with the goal of autonomously gathering both representative examples of the concepts and informative features for discriminating between the concepts. I led two investigations for the project on managing interaction with a human teacher, both described below.Īctive Learning of Grounded Concepts using Diverse Types of Learning Queries The agent learns to ground all task-relevant concepts by actively querying its human partner for relevant information. cooking pot, pasta sauce) it must perceptually ground, in order to later recognize instances of these concepts in the situated environment and use them to perform the task. serving pasta) and with it, task relevant concepts ( e.g. Assuming no prior knowledge, the learning agent is given a task ( e.g. ![]() In this thread of work, the agent no longer plays the role of passive observer it becomes an active questioner. ![]() ![]() My later work explored strategies for enabling a social robot learner to autonomously manage its own learning interactions with a human teacher, towards actively gathering diverse types of task knowledge. Towards Intelligent Arbitration of Diverse Active Learning Queries (IROS, 2018) Īctive Learning in Realistic Human Settings (ICML Workshop on Human in the Loop Learning, 2020) It is inspired by the expressive decision-making capabilities of human learners.Īctive Learning within Constrained Environments through Imitation of an Expert Questioner (IJCAI, 2019) Overall, this later body of work gives rise to a richer communication and more flexible learning mechanism, where an agent can both (a) initiate different types of communication actions with a teacher and (b) adapt to the teacher’s time and availability constraints. We extended this framework to additionally optimize for the time and cognitive load constraints of the teacher, within the agent objective function. The agent infers both when to request help and what type of information to query, based on its expectation of learning progress. In later work, we contributed a general decision-theoretic active learning framework (left) that enables a learner to autonomously manage interaction with a human partner. Grounding Action Parameters from Demonstration (RO-MAN, 2016) Human-Driven Feature Selection for a Robotic Agent Learning Classification Tasks from Demonstration (ICRA, 2018) Such a cognitive load however is an unreasonable burden to place on users, particularly the expectation of tracking a robot’s knowledge over time, in a non-stationary environment (as is the case with real-world settings). This is because the agent played the role of passive observer, as is typically assumed in LfD settings. However, they also relied upon the ability of human partners to both be proficient at teaching and track a robot’s knowledge over time, so as to know what new information to provide and when. Accordingly, our findings validated the usefulness of exploiting user domain knowledge in this problem setting. The goal of this project was to leverage interaction with humans for enabling sample-efficient concept grounding. Our initial work investigated Learning from Demonstration (LfD) approaches for the acquisition of (1) training instances as examples of task-relevant concepts and (2) informative features for appropriately representing and discriminating between task-relevant concepts. Initial Work (Passive Learning from Demonstration). This thread of research examines the problem of enabling a social robotic agent to employ interaction with a human partner for efficiently learning to ground task-relevant concepts in its environment. Assuming no prior knowledge, this is particularly challenging in newly situated or non-stationary environments, where the robot has limited representative training data. An example of this may be that in order to learn to serve cooked pasta in a home, a robot must first ground concepts like cooking pot, stove, and bottle of pasta sauce. The robot must first perceptually ground each entity and concept within the recipe ( e.g. items, locations) in order to perform the task. More specifically, one key recurring challenge occurs when the robotic agent is given a high-level task, described by an abstract task plan. Thus in order to provide the desired assistance, these agents need the ability to dynamically acquire and expand their task domain knowledge. Personal robots and other embodied assistants ( e.g. self-driving vehicles, smart home systems) are largely intended to provide intuitive assistance to people in their daily lives, yet we cannot program all task intelligence they will need a priori.
0 Comments
Leave a Reply. |