English
Related papers

Related papers: Using Parameterized Black-Box Priors to Scale Up M…

200 papers

Legged robots are able to navigate complex terrains by continuously interacting with the environment through careful selection of contact sequences and timings. However, the combinatorial nature behind contact planning hinders the…

Reinforcement Learning (RL) is a powerful mathematical framework that allows robots to learn complex skills by trial-and-error. Despite numerous successes in many applications, RL algorithms still require thousands of trials to converge to…

Robotics · Computer Science 2022-08-03 Matthias Mayr , Konstantinos Chatzilygeroudis , Faseeh Ahmad , Luigi Nardi , Volker Krueger

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…

The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable…

Robotics · Computer Science 2020-02-18 Wenhao Yu , Jie Tan , Yunfei Bai , Erwin Coumans , Sehoon Ha

When gradient-based methods are impractical, black-box optimization (BBO) provides a valuable alternative. However, BBO often struggles with high-dimensional problems and limited trial budgets. In this work, we propose a novel approach…

Systems and Control · Electrical Eng. & Systems 2025-10-03 Riccardo Busetto , Manas Mejari , Marco Forgione , Alberto Bemporad , Dario Piga

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Machine Learning · Computer Science 2023-11-07 Tyler Westenbroek , Jacob Levy , David Fridovich-Keil

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of behavior-such as ones…

Machine Learning · Computer Science 2020-10-27 Yiming Zhang , Quan Vuong , Keith W. Ross

Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies. While highly general, their learning dynamics are often times heuristic and inflexible - exactly the limitations that…

Neural and Evolutionary Computing · Computer Science 2023-03-03 Robert Tjarko Lange , Tom Schaul , Yutian Chen , Tom Zahavy , Valentin Dallibard , Chris Lu , Satinder Singh , Sebastian Flennerhag

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in…

Machine Learning · Computer Science 2019-05-16 Narendra Patwardhan , Zequn Wang

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this…

Machine Learning · Computer Science 2018-06-13 Krzysztof Choromanski , Mark Rowland , Vikas Sindhwani , Richard E. Turner , Adrian Weller

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Robotics · Computer Science 2021-12-08 Michael James McDonald , Dylan Hadfield-Menell

In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control. We use a feature-based representation of the dynamics that allows the dynamics model…

Machine Learning · Computer Science 2016-03-16 Christopher Xie , Sachin Patil , Teodor Moldovan , Sergey Levine , Pieter Abbeel

We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly…

Machine Learning · Computer Science 2021-09-07 Chen-Yu Wei , Haipeng Luo

Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical constraints during training. While high-fidelity simulations…

Robotics · Computer Science 2023-09-28 Joonho Lee , Lukas Schroth , Victor Klemm , Marko Bjelonic , Alexander Reske , Marco Hutter

Climbing, crouching, bridging gaps, and walking up stairs are just a few of the advantages that quadruped robots have over wheeled robots, making them more suitable for navigating rough and unstructured terrain. However, executing such…

Robotics · Computer Science 2025-09-16 Guillaume Gagné-Labelle , Vassil Atanassov , Ioannis Havoutis

Guided policy search algorithms have been proven to work with incredible accuracy for not only controlling a complicated dynamical system, but also learning optimal policies from various unseen instances. One assumes true nature of the…

Systems and Control · Electrical Eng. & Systems 2020-10-02 Prakash Mallick , Zhiyong Chen , Mohsen Zamani

In this paper, with a view toward deployment of light-weight control frameworks for bipedal walking robots, we realize end-foot trajectories that are shaped by a single linear feedback policy. We learn this policy via a model-free and a…

Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Libing Yang , Yang Li , Long Chen

This paper presents a method for identifying mechanical parameters of robots or objects, such as their mass and friction coefficients. Key features are the use of off-the-shelf physics engines and the adaptation of a Bayesian optimization…

Robotics · Computer Science 2018-06-14 Shaojun Zhu , Andrew Kimmel , Kostas E. Bekris , Abdeslam Boularias

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward…

Robotics · Computer Science 2026-01-01 Dongyun Kang , Min-Gyu Kim , Tae-Gyu Song , Hajun Kim , Sehoon Ha , Hae-Won Park