Interactive Learning from Activity Description
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a language that is most appropriate for them. Compared with reward in reinforcement learning (RL), the description feedback is richer and allows for improved sample complexity. We develop a probabilistic framework and an algorithm that practically implements our protocol. Empirical results in two challenging request-fulfilling problems demonstrate the strengths of our approach: compared with RL baselines, it is more sample-efficient; compared with IL baselines, it achieves competitive success rates without requiring the teaching agent to be able to demonstrate the desired behavior using the learning agent's actions. Apart from empirical evaluation, we also provide theoretical guarantees for our algorithm under certain assumptions about the teacher and the environment.
Code (1)
Tasks
General Reinforcement LearningGrounded language learningImitation LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
ChEX: Interactive Localization and Region Description in Chest X-rays
Report generation models offer fine-grained textual interpretations of medical images like chest X-rays, yet they often lack interactivity (i.e. the ability to steer the generation process through user queries) and local…
Ordered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding
We introduce a novel representation called Ordered Atomic Activity for interactive scenario understanding. The representation decomposes each scenario into a set of ordered atomic activities, where each activity cons…
Activity RecognitionSalsaAgent: A multimodal embodied language model for interactive dance generation
Interaction between humanoids involves bidirectional and nonverbal reactivity, coordination and synchrony. Toward socially aware robots and interactive virtual agents, we present SalsaAgent, a language model that generat…
Interactive Inference under Information Constraints
We study the role of interactivity in distributed statistical inference under information constraints, e.g., communication constraints and local differential privacy. We focus on the tasks of goodness-of-fit testing and …
Density EstimationSituated Language Learning via Interactive Narratives
This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize t…
Decision MakingSequential Decision Making