Experimental Study on Reinforcement Learning-based Control of an Acrobot
- URL: http://arxiv.org/abs/2011.09246v2
- Date: Thu, 27 Jul 2023 10:09:57 GMT
- Title: Experimental Study on Reinforcement Learning-based Control of an Acrobot
- Authors: Leo Dostal, Alexej Bespalko, and Daniel A. Duecker
- Abstract summary: We present results on how artificial intelligence learns to control an Acrobot using reinforcement learning (RL)
We study the control of angular velocity of the Acrobot, as well as control of its total energy, which is the sum of the kinetic and the potential energy.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We present computational and experimental results on how artificial
intelligence (AI) learns to control an Acrobot using reinforcement learning
(RL). Thereby the experimental setup is designed as an embedded system, which
is of interest for robotics and energy harvesting applications. Specifically,
we study the control of angular velocity of the Acrobot, as well as control of
its total energy, which is the sum of the kinetic and the potential energy. By
this means the RL algorithm is designed to drive the angular velocity or the
energy of the first pendulum of the Acrobot towards a desired value. With this,
libration or full rotation of the unactuated pendulum of the Acrobot is
achieved. Moreover, investigations of the Acrobot control are carried out,
which lead to insights about the influence of the state space discretization,
the episode length, the action space or the mass of the driven pendulum on the
RL control. By further numerous simulations and experiments the effects of
parameter variations are evaluated.
Related papers
- Unsupervised Learning of Effective Actions in Robotics [0.9374652839580183]
Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's actions.
We propose an unsupervised algorithm to discretize a continuous motion space and generate "action prototypes"
We evaluate our method on a simulated stair-climbing reinforcement learning task.
arXiv Detail & Related papers (2024-04-03T13:28:52Z) - Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal
Locomotion Control [112.66677641636299]
This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots.
We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing.
This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
arXiv Detail & Related papers (2024-01-30T10:48:43Z) - On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer [6.1622717998840395]
We study the choice of action space in robot manipulation learning and sim-to-real transfer.
We train over 250 reinforcement learning(RL) agents in simulated reaching and pushing tasks.
The choice of spaces spans combinations of common action space design characteristics.
arXiv Detail & Related papers (2023-12-06T18:38:05Z) - A Q-learning approach to the continuous control problem of robot
inverted pendulum balancing [0.29008108937701327]
This study evaluates the application of a discrete action space reinforcement learning method (Q-learning) to the continuous control problem of robot inverted pendulum balancing.
A mathematical model of the system dynamics is implemented, deduced by curve fitting on data acquired from the real system.
arXiv Detail & Related papers (2023-12-05T10:40:48Z) - Reaching the Limit in Autonomous Racing: Optimal Control versus
Reinforcement Learning [66.10854214036605]
A central question in robotics is how to design a control system for an agile mobile robot.
We show that a neural network controller trained with reinforcement learning (RL) outperformed optimal control (OC) methods in this setting.
Our findings allowed us to push an agile drone to its maximum performance, achieving a peak acceleration greater than 12 times the gravitational acceleration and a peak velocity of 108 kilometers per hour.
arXiv Detail & Related papers (2023-10-17T02:40:27Z) - Active Exploration for Robotic Manipulation [40.39182660794481]
This paper proposes a model-based active exploration approach that enables efficient learning in sparse-reward robotic manipulation tasks.
We evaluate our proposed algorithm in simulation and on a real robot, trained from scratch with our method.
arXiv Detail & Related papers (2022-10-23T18:07:51Z) - Active Predicting Coding: Brain-Inspired Reinforcement Learning for
Sparse Reward Robotic Control Problems [79.07468367923619]
We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC)
We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards.
We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
arXiv Detail & Related papers (2022-09-19T16:49:32Z) - Autonomous Aerial Robot for High-Speed Search and Intercept Applications [86.72321289033562]
A fully-autonomous aerial robot for high-speed object grasping has been proposed.
As an additional sub-task, our system is able to autonomously pierce balloons located in poles close to the surface.
Our approach has been validated in a challenging international competition and has shown outstanding results.
arXiv Detail & Related papers (2021-12-10T11:49:51Z) - Accelerating Robotic Reinforcement Learning via Parameterized Action
Primitives [92.0321404272942]
Reinforcement learning can be used to build general-purpose robotic systems.
However, training RL agents to solve robotics tasks still remains challenging.
In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy.
We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
arXiv Detail & Related papers (2021-10-28T17:59:30Z) - Populations of Spiking Neurons for Reservoir Computing: Closed Loop
Control of a Compliant Quadruped [64.64924554743982]
We present a framework for implementing central pattern generators with spiking neural networks to obtain closed loop robot control.
We demonstrate the learning of predefined gait patterns, speed control and gait transition on a simulated model of a compliant quadrupedal robot.
arXiv Detail & Related papers (2020-04-09T14:32:49Z) - Autonomous Control of a Line Follower Robot Using a Q-Learning
Controller [4.306143768014156]
This paper presents a simulation based Q learning method to control a line follower robot.
Considering the unknown mechanical characteristics of the robot, system modeling and controller designing can be extremely challenging.
The simulation and experimental results are provided to evaluate the effectiveness of the proposed controller.
arXiv Detail & Related papers (2020-01-23T22:50:14Z)
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.