Related papers: Asymmetric self-play for automatic goal discovery …

Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies as Gaussian process regression can learn optimal actions…

We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challenges of learning…

Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning.…

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

In human-robot teams, humans often start with an inaccurate model of the robot capabilities. As they interact with the robot, they infer the robot's capabilities and partially adapt to the robot, i.e., they might change their actions based…

To be helpful assistants, AI agents must be aware of their own capabilities and limitations. This includes knowing when to answer from parametric knowledge versus using tools, when to trust tool outputs, and when to abstain or hedge. Such…

Cooperative artificial intelligence with human or superhuman proficiency in collaborative tasks stands at the frontier of machine learning research. Prior work has tended to evaluate cooperative AI performance under the restrictive…

In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a large diversity of goals, aiming to discover what is…

We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). We consider an episodic setting where in each…

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…

Generative model-based imitation learning methods have recently achieved strong results in learning high-complexity motor skills from human demonstrations. However, imitation learning of interactive policies that coordinate with humans in…

We study the class of reach-avoid dynamic games in which multiple agents interact noncooperatively, and each wishes to satisfy a distinct target criterion while avoiding a failure criterion. Reach-avoid games are commonly used to express…

To handle underspecified or ambiguous queries, AI assistants need a policy for managing their uncertainty to determine (a) when to guess the user intent and answer directly, (b) when to enumerate and answer multiple possible intents, and…

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this…

Learned visuomotor policies have shown considerable success as an alternative to traditional, hand-crafted frameworks for robotic manipulation. Surprisingly, an extension of these methods to the multiview domain is relatively unexplored. A…

Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a…

Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To…

Representation learning and unsupervised skill discovery can allow robots to acquire diverse and reusable behaviors without the need for task-specific rewards. In this work, we use unsupervised reinforcement learning to learn a latent…

Quantum entanglement has been recently demonstrated as a useful resource in conflicting interest games of incomplete information between two players, Alice and Bob [Pappa et al., Phys. Rev. Lett. 114, 020401 (2015)]. General setting for…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…