相关论文: SkiLD: Unsupervised Skill Discovery Guided by Fact…

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching…

When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what…

Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of…

We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors. CIC utilizes contrastive learning between…

Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access…

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these…

Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications.…

Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on maximizing the diversity of skills without considering…

Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on…

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

In the absence of external rewards, agents can still learn useful behaviors by identifying and mastering a set of diverse skills within their environment. Existing skill learning methods use mutual information objectives to incentivize each…

Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. But one distinct advantage of unsupervised over supervised…

Autonomously learning diverse behaviors without an extrinsic reward signal has been a problem of interest in reinforcement learning. However, the nature of learning in such mechanisms is unconstrained, often resulting in the accumulation of…

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…

Skills or low-level policies in reinforcement learning are temporally extended actions that can speed up learning and enable complex behaviours. Recent work in offline reinforcement learning and imitation learning has proposed several…

Embodied agents operating in human spaces must be able to master how their environment works: what objects can the agent use, and how can it use them? We introduce a reinforcement learning approach for exploration for interaction, whereby…

State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision…

Unsupervised skill discovery is a learning paradigm that aims to acquire diverse behaviors without explicit rewards. However, it faces challenges in learning complex behaviors and often leads to learning unsafe or undesirable behaviors. For…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…