相关论文: Language-Conditioned Goal Generation: a New Approa…

Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life. However, it remains unclear **whether LMs have the capacity to…

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract…

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates…

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…

Human intelligence's adaptability is remarkable, allowing us to adjust to new tasks and multi-modal environments swiftly. This skill is evident from a young age as we acquire new abilities and solve problems by imitating others or following…

The question of how an effective and efficient communication system can emerge in a population of agents that need to solve a particular task attracts more and more attention from researchers in many fields, including artificial…

This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise…

Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-person actors in partially-observable worlds. To achieve…

We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained…

We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of diverse types of knowledge including perceptual, semantic,…

In real-world scenarios, it is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks. Despite recent progress, most previous approaches adopt simple low-level…

Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better…

Robotic manipulation benefits from foundation models that describe goals, but today's agents still lack a principled way to learn from their own mistakes. We ask whether natural language can serve as feedback, an error-reasoning signal that…

Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process, but it may require many generations of trial and error. Alternatively, the lingua franca can be given by…

In recent years, several machine learning models have been proposed. They are trained with a language modelling objective on large-scale text-only data. With such pretraining, they can achieve impressive results on many Natural Language…

In this study, we address the issue of enabling an artificial intelligence agent to execute complex language instructions within virtual environments. In our framework, we assume that these instructions involve intricate linguistic…

A long-term goal of Artificial Intelligence is to build a language understanding system that allows a human to collaborate with a physical robot using language that is natural to the human. In this paper we highlight some of the challenges…

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…

Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment. While in real-world scenarios,…

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer,…