Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2402.06102v1
• Date: Thu, 8 Feb 2024 23:35:03 GMT
• Title: Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning
• Authors: Mohak Bhardwaj, Thomas Lampe, Michael Neunert, Francesco Romano, Abbas Abdolmaleki, Arunkumar Byravan, Markus Wulfmeier, Martin Riedmiller, Jonas Buchli
• Abstract summary: "Box o Flows" is an experimental control system for systematically evaluating RL algorithms in dynamic real-world scenarios. We show how state-of-the-art model-free RL algorithms can synthesize a variety of complex behaviors via simple reward specifications. We believe that the insights gained from this preliminary study and the availability of systems like the Box o Flows support the way forward for developing systematic RL algorithms.
• Score: 7.714620721734689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in real-world applications of reinforcement learning (RL) have relied on the ability to accurately simulate systems at scale. However, domains such as fluid dynamical systems exhibit complex dynamic phenomena that are hard to simulate at high integration rates, limiting the direct application of modern deep RL algorithms to often expensive or safety critical hardware. In this work, we introduce "Box o Flows", a novel benchtop experimental control system for systematically evaluating RL algorithms in dynamic real-world scenarios. We describe the key components of the Box o Flows, and through a series of experiments demonstrate how state-of-the-art model-free RL algorithms can synthesize a variety of complex behaviors via simple reward specifications. Furthermore, we explore the role of offline RL in data-efficient hypothesis testing by reusing past experiences. We believe that the insights gained from this preliminary study and the availability of systems like the Box o Flows support the way forward for developing systematic RL algorithms that can be generally applied to complex, dynamical systems. Supplementary material and videos of experiments are available at https://sites.google.com/view/box-o-flows/home.

Related papers

• Controlling dynamical systems to complex target states using machine learning: next-generation vs. classical reservoir computing [68.8204255655161]
  Controlling nonlinear dynamical systems using machine learning allows to drive systems into simple behavior like periodicity but also to more complex arbitrary dynamics. We show first that classical reservoir computing excels at this task. In a next step, we compare those results based on different amounts of training data to an alternative setup, where next-generation reservoir computing is used instead. It turns out that while delivering comparable performance for usual amounts of training data, next-generation RC significantly outperforms in situations where only very limited data is available.
  arXiv  Detail & Related papers  (2023-07-14T07:05:17Z)
• Efficient Reinforcement Learning Through Trajectory Generation [5.766441610380447]
  A key barrier to using reinforcement learning in real-world applications is the requirement of a large number of system interactions to learn a good control policy. Off-policy and Offline RL methods have been proposed to reduce the number of interactions with the physical environment by learning control policies from historical data. We propose a trajectory generation algorithm, which adaptively generates new trajectories as if the system is being operated and explored under the updated control policies.
  arXiv  Detail & Related papers  (2022-11-30T18:49:43Z)
• Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systems [17.10464381844892]
  Reinforcement learning (RL) is highly suitable for devising control strategies in the context of dynamical systems. Recent research results indicate that RL-augmented computational fluid dynamics (CFD) solvers can exceed the current state of the art. We present Relexi as a scalable RL framework that bridges the gap between machine learning and modern CFD solvers on HPC systems.
  arXiv  Detail & Related papers  (2022-05-13T08:21:18Z)
• Accelerated Policy Learning with Parallel Differentiable Simulation [59.665651562534755]
  We present a differentiable simulator and a new policy learning algorithm (SHAC) Our algorithm alleviates problems with local minima through a smooth critic function. We show substantial improvements in sample efficiency and wall-clock time over state-of-the-art RL and differentiable simulation-based algorithms.
  arXiv  Detail & Related papers  (2022-04-14T17:46:26Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems [18.281902746944525]
  In this paper, we study how to build lightweight simulators of complicated systems that can run sufficiently fast for deep RL. We focus on domains where agents interact with a reduced portion of a larger environment while still being affected by the global dynamics. Our method combines the use of local simulators with learned models that mimic the influence of the global system.
  arXiv  Detail & Related papers  (2022-02-03T11:33:58Z)
• Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning [9.428825075908131]
  We propose an abstraction-based approach to train DRL systems on finite abstract domains. It yields neural networks whose input states are finite, making hosting DRL systems directly verifiable.
  arXiv  Detail & Related papers  (2021-06-13T06:28:40Z)
• Controlling nonlinear dynamical systems into arbitrary states using machine learning [77.34726150561087]
  We propose a novel and fully data driven control scheme which relies on machine learning (ML) Exploiting recently developed ML-based prediction capabilities of complex systems, we demonstrate that nonlinear systems can be forced to stay in arbitrary dynamical target states coming from any initial state. Having this highly flexible control scheme with little demands on the amount of required data on hand, we briefly discuss possible applications that range from engineering to medicine.
  arXiv  Detail & Related papers  (2021-02-23T16:58:26Z)
• Learning Dexterous Manipulation from Suboptimal Experts [69.8017067648129]
  Relative Entropy Q-Learning (REQ) is a simple policy algorithm that combines ideas from successful offline and conventional RL algorithms. We show how REQ is also effective for general off-policy RL, offline RL, and RL from demonstrations.
  arXiv  Detail & Related papers  (2020-10-16T18:48:49Z)
• Information Theoretic Model Predictive Q-Learning [64.74041985237105]
  We present a novel theoretical connection between information theoretic MPC and entropy regularized RL. We develop a Q-learning algorithm that can leverage biased models.
  arXiv  Detail & Related papers  (2019-12-31T00:29:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.