For robots to interact effectively with human users they must be capable of coordinated, timely behavior in response to social context. The Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project focuses on the design of long-term, adaptive social interaction between robots and child users in real-world settings. In this paper, we report on the iterative approach taken to scientific and technical developments toward this goal: advancing individual technical competencies and integrating them to form an autonomous robotic system for evaluation "in the wild." The first evaluation iterations have shown the potential of this methodology in terms of adaptation of the robot to the interactant and the resulting influences on engagement. This sets the foundation for an ongoing research program that seeks to develop technologies for social robot companions.
Abstract-Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems due to large search spaces. This paper proposes a three-stage method for multi-domain dialogue policy learning-termed NDQN, and applies it to an informationseeking spoken dialogue system in the domains of restaurants and hotels. In this method, the first stage does multi-policy learning via a network of DQN agents; the second makes use of compact state representations by compressing raw inputs; and the third stage applies a pre-training phase for bootstraping the behaviour of agents in the network. Experimental results comparing DQN (baseline) versus NDQN (proposed) using simulations report that the proposed method exhibits better scalability and is promising for optimising the behaviour of multi-domain dialogue systems. An additional evaluation reports that the NDQN agents outperformed a K-Nearest Neighbour baseline in task success and dialogue length, yielding more efficient and successful dialogues.
Natural Language Generation systems in interactive settings often face a multitude of choices, given that the communicative effect of each utterance they generate depends crucially on the interplay between its physical circumstances, addressee and interaction history. This is particularly true in interactive and situated settings. In this paper we present a novel approach forsituated Natural Language Generationin dialogue that is based onhierarchical reinforcement learningand learns the best utterance for a context by optimisation through trial and error. The model is trained from human–human corpus data and learns particularly to balance the trade-off betweenefficiencyanddetailin giving instructions: the user needs to be given sufficient information to execute their task, but without exceeding their cognitive load. We present results from simulation and a task-based human evaluation study comparing two different versions of hierarchical reinforcement learning: One operates using a hierarchy of policies with a large state space and local knowledge, and the other additionally shares knowledge across generation subtasks to enhance performance. Results show that sharing knowledge across subtasks achieves better performance than learning in isolation, leading to smoother and more successful interactions that are better perceived by human users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.