相关论文: Learning and Exploiting Multiple Subgoals for Fast…

Hierarchical Reinforcement Learning (HRL) agents have the potential to demonstrate appealing capabilities such as planning and exploration with abstraction, transfer, and skill reuse. Recent successes with HRL across different domains…

Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks due to the difficulty in designing comprehensive and precise reward functions. This inherent difficulty curtails the broader…

Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of…

Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we…

Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this…

Two common approaches to sequential decision-making are AI planning (AIP) and reinforcement learning (RL). Each has strengths and weaknesses. AIP is interpretable, easy to integrate with symbolic knowledge, and often efficient, but requires…

The autonomous exploration of environments by multi-robot systems is a critical task with broad applications in rescue missions, exploration endeavors, and beyond. Current approaches often rely on either greedy frontier selection or…

Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including…

In this paper, a unified framework for exploration in reinforcement learning (RL) is proposed based on an option-critic model. The proposed framework learns to integrate a set of diverse exploration strategies so that the agent can…

Learning in high-dimensional action spaces is a key challenge in applying reinforcement learning (RL) to real-world systems. In this paper, we study the possibility of controlling power networks using RL methods. Power networks are critical…

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able…

Reinforcement learning (RL) is a general and well-known method that a robot can use to learn an optimal control policy to solve a particular task. We would like to build a versatile robot that can learn multiple tasks, but using RL for each…

Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of…

Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration requires agents to possess higher-level cognitive abilities,…

Reward design is a fundamental, yet challenging aspect of reinforcement learning (RL). Researchers typically utilize feedback signals from the environment to handcraft a reward function, but this process is not always effective due to the…

Despite the significant success at enabling robots with autonomous behaviors makes deep reinforcement learning a promising approach for robotic object search task, the deep reinforcement learning approach severely suffers from the nature…

Modern listwise recommendation systems need to consider both long-term user perceptions and short-term interest shifts. Reinforcement learning can be applied on recommendation to study such a problem but is also subject to large search…

Exploration in environments with sparse rewards remains a fundamental challenge in reinforcement learning (RL). Existing approaches such as curriculum learning and Go-Explore often rely on hand-crafted heuristics, while curiosity-driven…

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or…

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction…