skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, October 10 until 2:00 AM ET on Friday, October 11 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the NSF-PAR

Title: CONTINUAL LEARNING AND PRIVATE UNLEARNING
As intelligent agents become autonomous over longer periods of time, they may eventually be- come lifelong counterparts to specific people. If so, it may be common for a user to want the agent to master a task temporarily but later on to forget the task due to privacy concerns. How- ever enabling an agent to forget privately what the user specified without degrading the rest of the learned knowledge is a challenging problem. With the aim of addressing this challenge, this paper formalizes this continual learning and private unlearning (CLPU) problem. The pa- per further introduces a straightforward but exactly private solution, CLPU-DER++, as the first step towards solving the CLPU problem, along with a set of carefully designed benchmark prob- lems to evaluate the effectiveness of the proposed solution.  more » « less
Award ID(s):
1846421
NSF-PAR ID:
10440559
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Advances in neural information processing systems
ISSN:
1049-5258
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , 2022 International Joint Conference on Neural Networks (IJCNN))
    Teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments is a challenging problem. We consider that user defines every task by a linear temporal logic (LTL) formula. However, some causal dependencies in complex environments may be unknown to the user in advance. Hence, when human user is specifying instructions, the robot cannot solve the tasks by simply following the given instructions. In this work, we propose a hierarchical reinforcement learning (HRL) framework in which a symbolic transition model is learned to efficiently produce high-level plans that can guide the agent efficiently solve different tasks. Specifically, the symbolic transition model is learned by inductive logic programming (ILP) to capture logic rules of state transitions. By planning over the product of the symbolic transition model and the automaton derived from the LTL formula, the agent can resolve causal dependencies and break a causally complex problem down into a sequence of simpler low-level sub-tasks. We evaluate the proposed framework on three environments in both discrete and continuous domains, showing advantages over previous representative methods. 
    more » « less
  2. ; ; ; ( , International Conference on Principles of Knowledge Representation and Reasoning ()
    null (Ed.)
    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming. 
    more » « less
  3. ; ; ; ( , Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning)
    null (Ed.)

    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming.

     
    more » « less
  4. ; ; ; ( , CHI 2019 Workshop on Conversational Agents: Acting on the Wave of Research and Development (CHI19convai))
    A major challenge in designing conversational agents is to handle unknown concepts in user utterances. This is particularly difficult for general-purpose task-oriented agents, as the unknown concepts and the tasks can be outside of the agent’s existing domain of knowledge. In this work, we propose a new multi-modal mixed-initiative approach towards this problem. Our agent Pumice guides the user to recursively explain unknown concepts through conversations, and to ground these concepts by demonstrating on the graphical user interfaces (GUIs) of existing third-party mobile apps. Pumice also supports the generalization of learned concepts to other different contexts and task domains. 
    more » « less
  5. ; ; ; ; ; ; ( , Proceedings of the International Conference on Automated Planning and Scheduling)
    In a multi-agent path finding (MAPF) problem, the task is to move a set of agents to their goal locations without conflicts. In the real world, unexpected events may delay some of the agents. In this paper, we therefore study the problem of finding a p-robust solution to a given MAPF problem, which is a solution that succeeds with probability at least p, even though unexpected delays may occur. We propose two methods for verifying that given solutions are p-robust. We also introduce an optimal CBS-based algorithm, called pR-CBS, and a fast suboptimal algorithm, called pR-GCBS, for finding such solutions. Our experiments show that a p-robust solution reduces the number of conflicts compared to optimal, non-robust solutions. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email