中文
相关论文

相关论文: "What are my options?": Explaining RL Agents with …

200 篇论文

This paper explores the problem of simultaneously learning a value function and policy in deep actor-critic reinforcement learning models. We find that the common practice of learning these functions jointly is sub-optimal, due to an…

机器学习 · 计算机科学 2022-11-15 Matthew Aitchison , Penny Sweetser

Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends…

Consider the problem of training robustly capable agents. One approach is to generate a diverse collection of agent polices. Training can then be viewed as a quality diversity (QD) optimization problem, where we search for a collection of…

机器学习 · 计算机科学 2022-04-18 Bryon Tjanaka , Matthew C. Fontaine , Julian Togelius , Stefanos Nikolaidis

Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and…

机器学习 · 计算机科学 2022-10-05 Per-Arne Andersen , Ole-Christoffer Granmo , Morten Goodwin

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

机器学习 · 计算机科学 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were…

神经与进化计算 · 计算机科学 2023-09-11 Felix Chalumeau , Raphael Boige , Bryan Lim , Valentin Macé , Maxime Allard , Arthur Flajolet , Antoine Cully , Thomas Pierrot

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

机器学习 · 计算机科学 2024-01-03 Guojian Wang , Faguo Wu , Xiao Zhang , Ning Guo , Zhiming Zheng

Reinforcement learning (RL) involves sequential decision making in uncertain environments. The aim of the decision-making agent is to maximize the benefit of acting in its environment over an extended period of time. Finding an optimal…

人工智能 · 计算机科学 2007-05-23 Istvan Szita , Balint Takacs , Andras Lorincz

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,…

人工智能 · 计算机科学 2022-01-05 Tom Zahavy , Brendan O'Donoghue , Andre Barreto , Volodymyr Mnih , Sebastian Flennerhag , Satinder Singh

Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently…

机器学习 · 计算机科学 2019-06-04 Muhammad A. Masood , Finale Doshi-Velez

When tackling complex problems, humans naturally break them down into smaller, manageable subtasks and adjust their initial plans based on observations. For instance, if you want to make coffee at a friend's place, you might initially plan…

人工智能 · 计算机科学 2025-05-20 Zihan Ye , Oleg Arenz , Kristian Kersting

Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has become a useful reinforcement learning (RL) framework for…

机器学习 · 计算机科学 2026-05-13 Cornelius V. Braun , Sayantan Auddy , Marc Toussaint

Autonomous 3D environment exploration is a fundamental task for various applications such as navigation. The goal of exploration is to investigate a new environment and build its occupancy map efficiently. In this paper, we propose a new…

人工智能 · 计算机科学 2021-11-03 Liu Juncheng , McCane Brendan , Mills Steven

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,…

In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjusting the width and depth in a differentiable manner. The…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Shaopeng Guo , Yujie Wang , Kun Yuan , Quanquan Li

Augmenting an agent's control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options is infeasible in high-dimensional and abstract state spaces.…

机器学习 · 计算机科学 2017-10-06 Roy Fox , Sanjay Krishnan , Ion Stoica , Ken Goldberg

Reinforcement learning methods typically use Deep Neural Networks to approximate the value functions and policies underlying a Markov Decision Process. Unfortunately, DNN-based RL suffers from a lack of explainability of the resulting…

系统与控制 · 电气工程与系统科学 2022-05-19 Shambhuraj Sawant , Sebastien Gros

Many environments contain numerous available niches of variable value, each associated with a different local optimum in the space of behaviors (policy space). In such situations it is often difficult to design a learning process capable of…

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

机器学习 · 计算机科学 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or…

机器学习 · 计算机科学 2024-01-09 Wentse Chen , Shiyu Huang , Yuan Chiang , Tim Pearce , Wei-Wei Tu , Ting Chen , Jun Zhu
‹ 上一页 1 2 3 10 下一页 ›