Related papers: Focused Skill Discovery: Learning to Control Speci…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods are often limited to acquiring simple, easy-to-learn skills…
Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to…
Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors and solve diverse…
In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control)…
Reinforcement learning provides a general framework for learning robotic skills while minimizing engineering effort. However, most reinforcement learning algorithms assume that a well-designed reward function is provided, and learn a single…
Tasks where the set of possible actions depend discontinuously on the state pose a significant challenge for current reinforcement learning algorithms. For example, a locked door must be first unlocked, and then the handle turned before the…
Skill acquisition is a key area of research in cognitive psychology as it encompasses multiple psychological processes. The laws discovered under experimental paradigms are controversial and lack generalizability. This paper aims to unearth…
Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an…
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization…
A parameterized skill is a mapping from multiple goals/task parameters to the policy parameters to accomplish them. Existing works in the literature show how a parameterized skill can be learned given a task space that defines all the…
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…
Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based…
We address the problem of effectively composing skills to solve sparse-reward tasks in the real world. Given a set of parameterized skills (such as exerting a force or doing a top grasp at a location), our goal is to learn policies that…
It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around:…
Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact,…
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…
Policy search reinforcement learning allows robots to acquire skills by themselves. However, the learning procedure is inherently unsafe as the robot has no a-priori way to predict the consequences of the exploratory actions it takes.…
Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces…