相关论文: Unsupervised Learning of Efficient Exploration: Pr…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding the most useful…

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks.…

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…

For reinforcement learning agents to be deployed in high-risk settings, they must achieve a high level of robustness to unfamiliar scenarios. One method for improving robustness is unsupervised environment design (UED), a suite of methods…

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous…

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…

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…

In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

Unsupervised reinforcement learning aims to train agents to learn a handful of policies or skills in environments without external reward. These pre-trained policies can accelerate learning when endowed with external reward, and can also be…

Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e.,…

Reinforcement Learning (RL) algorithms are often known for sample inefficiency and difficult generalization. Recently, Unsupervised Environment Design (UED) emerged as a new paradigm for zero-shot generalization by simultaneously learning a…

Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challenge in unsupervised RL is to extract behaviors that…

A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations. This challenge motivates the problem setting of Unsupervised Environment…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement…

Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing approaches suffer from several limitations: they may require…