Related papers: Learning New Skills after Deployment: Improving op…
On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be…
Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we…
Neural conversation models are attractive because one can train a model directly on dialog examples with minimal labeling. With a small amount of data, however, they often fail to generalize over test data since they tend to capture…
Current dialogue systems are not very engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models…
Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the…
Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…
It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system…
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…
Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for LLMs has largely focused on domains like code and math,…
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant recent advances in neural conversational systems using large…
In this paper, we describe a set of metrics for the evaluation of different dialogue management strategies in an implemented real-time spoken language system. The set of metrics we propose offers useful insights in evaluating how particular…
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…
Surgical skill directly affects surgical procedure outcomes; thus, effective training is needed to ensure satisfactory results. Many objective assessment metrics have been developed and some are widely used in surgical training simulators.…
Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…
Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories. Such method follows the supervised learning paradigm and it strongly…
Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are. Being informative is unfortunately very challenging, because during teaching, people typically get no…
Natural language understanding for robotics can require substantial domain- and platform-specific engineering. For example, for mobile robots to pick-and-place objects in an environment to satisfy human commands, we can specify the language…
We propose a method for training language models in an interactive setting inspired by child language acquisition. In our setting, a speaker attempts to communicate some information to a listener in a single-turn dialogue and receives a…