Related papers: Training an Interactive Humanoid Robot Using Multi…

Multi-robot navigation is a challenging task in which multiple robots must be coordinated simultaneously within dynamic environments. We apply deep reinforcement learning (DRL) to learn a decentralized end-to-end policy which maps raw…

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level"…

Soft robots have the potential to revolutionize the use of robotic systems with their capability of establishing safe, robust, and adaptable interactions with their environment, but their precise control remains challenging. In contrast,…

We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual…

Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In…

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from…

We tackle the problem of developing humanoid loco-manipulation skills with deep imitation learning. The difficulty of collecting task demonstrations and training policies for humanoids with a high degree of freedom presents substantial…

As robots enter human environments, they will be expected to accomplish a tremendous range of tasks. It is not feasible for robot designers to pre-program these behaviors or know them in advance, so one way to address this is through…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…

Natural-language dialog is key for intuitive human-robot interaction. It can be used not only to express humans' intents, but also to communicate instructions for improvement if a robot does not understand a command correctly. Of great…

Understanding action correspondence between humans and robots is essential for evaluating alignment in decision-making, particularly in human-robot collaboration and imitation learning within unstructured environments. We propose a…

Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…

Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…

The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and…

Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…

To improve the cognitive autonomy of humanoid robots, this research proposes a multi-scenario reasoning architecture to solve the technical shortcomings of multi-modal understanding in this field. It draws on simulation based experimental…

Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…

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…