相关论文: Learning to Discover Skills through Guidance

Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility (UAM) and Unmanned Aircraft System (UAS) Traffic Management (UTM). There are many techniques for real-time robust drone guidance, but many…

We propose a robotic learning system for autonomous exploration and navigation in unexplored environments. We are motivated by the idea that even an unseen environment may be familiar from previous experiences in similar environments. The…

Concept drift detection is a crucial task in data stream evolving environments. Most of state of the art approaches designed to tackle this problem monitor the loss of predictive models. However, this approach falls short in many real-world…

Many people hold a vision that big data will provide big insights and have a big impact in the future, and big-data-assisted scientific discovery is seen as an emerging and promising scientific paradigm. However, how to turn big data into…

We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown environment without observing external rewards. Reward-free exploration aims to enable…

Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstream tasks. As the agent cannot access extrinsic rewards during…

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Learning policies via preference-based reward learning is an increasingly popular method for customizing agent behavior, but has been shown anecdotally to be prone to spurious correlations and reward hacking behaviors. While much prior work…

Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximization or variational…

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:…

Behavior domination is proposed as a tool for understanding and harnessing the power of evolutionary systems to discover and exploit useful stepping stones. Novelty search has shown promise in overcoming deception by collecting diverse…

Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap between the two domains. While some methods address target…

In actor-critic-based reinforcement learning algorithms such as Twin Delayed Deep Deterministic policy gradient (TD3), insufficient exploration of the spatial space can result in suboptimal policies when controlling 7-DOF robotic arms. To…

Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of…

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…

In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature…

Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer,…

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference…

One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration,…

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…