Search Results for author:
Found 33 papers, 6 papers with code
Handling Reward Misspecification in the Presence of Expectation Mismatch
Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research.
Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning
This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks.
TOBY: A Tool for Exploring Data in Academic Survey Papers
This paper describes TOBY, a visualization tool that helps a user explore the contents of an academic survey paper.
On the Planning Abilities of Large Language Models : A Critical Investigation
We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs in LLM-Modulo settings where they act as a source of heuristic guidance for external planners and verifiers.
Planning for Attacker Entrapment in Adversarial Settings
In this paper, we propose a planning framework to generate a defense strategy against an attacker who is working in an environment where a defender can operate without the attacker's knowledge.
On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)
On this benchmark, we evaluate LLMs in three modes: autonomous, heuristic and human-in-the-loop.
Goal Alignment: A Human-Aware Account of Value Alignment Problem
To address this lacuna, we propose a novel formulation for the value alignment problem, named goal alignment that focuses on a few central challenges related to value alignment.
A Mental Model Based Theory of Trust
Handling trust is one of the core requirements for facilitating effective interaction between the human and the AI agent.
Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
If the relevant concept is not in the shared vocabulary, then it is learned.
PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
PlanBench provides sufficient diversity in both the task domains and the specific planning capabilities.
A Mental-Model Centric Landscape of Human-AI Symbiosis
Through this paper, we will see how this new framework allows us to capture the various works done in the space of human-AI interaction and identify the fundamental behavioral patterns supported by these works.
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
At the low level, we learn a set of diverse policies for each possible task subgoal identified by the landmark, which are then stitched together.
Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems
The jury is still out on whether AI systems will need to use symbols in their internal reasoning to achieve general intelligence capabilities.
Not all users are the same: Providing personalized explanations for sequential decision making problems
The former is achieved by a data-driven clustering approach while for the latter, we compile our explanation generation problem into a POMDP.
GPT3-to-plan: Extracting plans from text using GPT-3
Operations in many essential industries including finance and banking are often characterized by the need to perform repetitive sequential tasks.
Trust-Aware Planning: Modeling Trust Evolution in Iterated Human-Robot Interaction
The problem of trust management is particularly challenging in mixed human-robot teams where the human and the robot may have different models about the task at hand and thus may have different expectations regarding the current course of action, thereby forcing the robot to focus on the costly explicable behavior.
A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI
Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation.
A Bayesian Account of Measures of Interpretability in Human-AI Interaction
Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation.
Explainable Composition of Aggregated Assistants
A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" -- realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks.
RADAR-X: An Interactive Mixed Initiative Planning Interface Pairing Contrastive Explanations and Revised Plan Suggestions
Decision support systems seek to enable informed decision-making.
Designing Environments Conducive to Interpretable Robot Behavior
Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior.
The Emerging Landscape of Explainable AI Planning and Decision Making
In this paper, we provide a comprehensive outline of the different threads of work in Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years and contrast that with earlier efforts in the field in terms of techniques, target users, and delivery mechanisms.
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations
As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions.
Why Couldn't You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice
Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans.
Expectation-Aware Planning: A Unifying Framework for Synthesizing and Executing Self-Explaining Plans for Human-Aware Planning
In this work, we present a new planning formalism called Expectation-Aware planning for decision making with humans in the loop where the human's expectations about an agent may differ from the agent's own model.
Model-Free Model Reconciliation
One such approach has been the idea of {\em explanation as model-reconciliation}.
Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior
There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop.
Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations
There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users.
Plan Explanations as Model Reconciliation -- An Empirical Study
Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same, and how the explanation process as a result of this mismatch can be then seen as a process of reconciliation of these models.
Balancing Explicability and Explanation in Human-Aware Planning
In this paper, we bring these two concepts together and show how a planner can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA.
Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy
When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior.
Compliant Conditions for Polynomial Time Approximation of Operator Counts
In this paper, we develop a computationally simpler version of the operator count heuristic for a particular class of domains.
Plan Explicability and Predictability for Robot Task Planning
Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans.
