English
Related papers

Related papers: Physical Derivatives: Computing policy gradients b…

200 papers

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine Learning · Computer Science 2024-03-19 Jan Schneider , Pierre Schumacher , Simon Guist , Le Chen , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

Modern robotics is gravitating toward increasingly collaborative human robot interaction. Tools such as acceleration policies can naturally support the realization of reactive, adaptive, and compliant robots. These tools require us to model…

Robotics · Computer Science 2017-10-09 Daniel Kappler , Franziska Meier , Nathan Ratliff , Stefan Schaal

Reinforcement learning (RL) shows great potential in sequential decision-making. At present, mainstream RL algorithms are data-driven, which usually yield better asymptotic performance but much slower convergence compared with model-driven…

Machine Learning · Computer Science 2024-02-27 Yang Guan , Jingliang Duan , Shengbo Eben Li , Jie Li , Jianyu Chen , Bo Cheng

Reinforcement learning (RL) has demonstrated the ability to maintain the plasticity of the policy throughout short-term training in aerial robot control. However, these policies have been shown to loss of plasticity when extended to…

Robotics · Computer Science 2025-03-11 Ali Tahir Karasahin , Ziniu Wu , Basaran Bahadir Kocer

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from…

Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventional method for…

Machine Learning · Computer Science 2023-11-08 Firas Al-Hafez , Guoping Zhao , Jan Peters , Davide Tateo

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Machine Learning · Computer Science 2020-08-12 Suraj Nair , Silvio Savarese , Chelsea Finn

Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement…

Robotics · Computer Science 2023-10-17 Yu-Ming Chen , Hien Bui , Michael Posa

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient…

Machine Learning · Computer Science 2023-06-13 Louis Fournier , Stéphane Rivaud , Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

Machine Learning · Computer Science 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence guarantees. This is in sharp contrast to classical model-based control,…

Optimization and Control · Mathematics 2020-06-16 Guannan Qu , Chenkai Yu , Steven Low , Adam Wierman

The networked nature of multi-robot systems presents challenges in the context of multi-agent reinforcement learning. Centralized control policies do not scale with increasing numbers of robots, whereas independent control policies do not…

Robotics · Computer Science 2025-06-24 Eduardo Sebastian , Thai Duong , Nikolay Atanasov , Eduardo Montijano , Carlos Sagues

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…

Machine Learning · Computer Science 2026-04-03 Klemens Iten , Bruce Lee , Chenhao Li , Lenart Treven , Andreas Krause , Bhavya Sukhija

A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive…

Machine Learning · Computer Science 2021-06-29 Alvaro Ovalle , Simon M. Lucas

Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are…

Robotics · Computer Science 2026-04-27 Shihan Wu , Xu Luo , Ji Zhang , Junlin Xie , Jingkuan Song , Heng Tao Shen , Lianli Gao

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Robotics · Computer Science 2024-10-28 Uljad Berdica , Matthew Jackson , Niccolò Enrico Veronese , Jakob Foerster , Perla Maiolino

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

Machine Learning · Computer Science 2023-10-30 Gaon An , Junhyeok Lee , Xingdong Zuo , Norio Kosaka , Kyung-Min Kim , Hyun Oh Song