Search Results for author:
Found 22 papers, 3 papers with code
Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach
In this framework, an LLM is paired with a complete set of sound verifiers that validate its output, re-prompting it if it fails.
Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning
As the applicability of Large Language Models (LLMs) extends beyond traditional text processing tasks, there is a burgeoning interest in their potential to excel in planning and reasoning assignments, realms traditionally reserved for System 2 cognitive competencies.
On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
In this paper we examine these claims of ReAct based prompting in improving agentic LLMs for sequential decision-making.
Hindsight PRIORs for Reward Learning from Human Preferences
Incorporating state importance into reward learning improves the speed of policy learning, overall policy performance, and reward recovery on both locomotion and manipulation tasks.
LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
On the other side are perhaps over-pessimistic claims that all that LLMs are good for in planning/reasoning tasks are as mere translators of the problem specification from one syntactic format to another, and ship the problem off to external symbolic solvers.
Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?
In this work, we explore the task of Perceived Behavior Recognition, where a robot employs a Large Language Model (LLM) to assess the robot's generated behavior in a manner similar to human observer.
Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming
To this end, we perform the first investigation of multi-agent PbRL by extending single-agent PbRL to the two-agent teaming settings and formulate it as a Human-AI PbRL Cooperation Game, where the RL agent queries the human-in-the-loop to elicit task objective and human's preferences on the joint team behavior.
Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments
Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance.
Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning
Preference Based Reinforcement Learning has shown much promise for utilizing human binary feedback on queried trajectory pairs to recover the underlying reward model of the Human in the Loop (HiL).
A State Augmentation based approach to Reinforcement Learning from Human Preferences
Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains.
Data Driven Reward Initialization for Preference based Reinforcement Learning
We propose a data-driven reward initialization method that does not add any additional cost to the human in the loop and negligible cost to the PbRL agent and show that doing so ensures that the predicted rewards of the initialized reward model are uniform in the state space and this reduces the variability in the performance of the method across multiple runs and is shown to improve the overall performance compared to other initialization methods.
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.
Symbol Guided Hindsight Priors for Reward Learning from Human Preferences
Specifying rewards for reinforcement learned (RL) agents is challenging.
Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop
Through our experiments, we show that our method can provide an interpretable means of solving the Advice-Conformance Verification problem by conveying whether or not the agent is using the human's advice.
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.
Computing Policies That Account For The Effects Of Human Agent Uncertainty During Execution In Markov Decision Processes
We present a framework to model the human agent's behavior with respect to state uncertainty, and can be used to compute MDP policies that accounts for these problems.
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 Novel Framework for Neural Architecture Search in the Hill Climbing Domain
Neural networks have now long been used for solving complex problems of image domain, yet designing the same needs manual expertise.
Fine-grained Language Identification with Multilingual CapsNet Model
Hence, there is an increasing need for real-time and fine-grained content analysis services, including language identification, content transcription, and analysis.
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
We focus on the task of learning from feedback, in which the human trainer not only gives binary evaluative "good" or "bad" feedback for queried state-action pairs, but also provides a visual explanation by annotating relevant features in images.
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.
Making Smart Homes Smarter: Optimizing Energy Consumption with Human in the Loop
Rapid advancements in the Internet of Things (IoT) have facilitated more efficient deployment of smart environment solutions for specific user requirement.
