Control of Inverted Double Pendulum using Reinforcement Learning
نویسنده
چکیده
In this project, we apply reinforcement learning techniques to control an inverted double pendulum on a cart. We successfully learn a controller for balancing in a simulation environment using Qlearning with a linear function approximator, without any prior knowledge of the system at hand. We do however fail to learn a controller for the swingup maneuver, which leads to a discussion on what might be needed to solve more complex control problems using reinforcement learning.
منابع مشابه
Q Learning based Reinforcement Learning Approach to Bipedal Walking Control
Reinforcement learning has been active research area not only in machine learning but also in control engineering, operation research and robotics in recent years. It is a model free learning control method that can solve Markov decision problems. Q-learning is an incremental dynamic programming procedure that determines the optimal policy in a step-by-step manner. It is an online procedure for...
متن کاملInverted Pendulum Control Using Negative Data
In the training phase of learning algorithms, it is always important to have a suitable training data set. The presence of outliers, noise data, and inappropriate data always affects the performance of existing algorithms. The active learning method (ALM) is one of the powerful tools in soft computing inspired by the computation of the human brain. The operation of this algorithm is complete...
متن کاملReinforcement Learning with Perturbation Method to Turn Unidirectional Linear Response Fuzzy Controller for Inverted Pendulum
In this paper, we present a unidirectional linear response fuzzy controller (FC) to control the inverted pendulum system. The performance of turning fuzzy controller is defined as an evaluation function and our proposed technique, which is based on the integration of reinforcement learning and a perturbation method, is utilized to diversity the search of minimization of the evaluation function....
متن کاملQ-Value Based Particle Swarm Optimization for Reinforcement Neuro- Fuzzy System Design
This paper proposes a combination of particle swarm optimization (PSO) and Q-value based safe reinforcement learning scheme for neuro-fuzzy systems (NFS). The proposed Q-value based particle swarm optimization (QPSO) fulfills PSO-based NFS with reinforcement learning; that is, it provides PSO-based NFS an alternative to learn optimal control policies under environments where only weak reinforce...
متن کاملUsing Assembler Encoding to Solve Inverted Pendulum Problem
Assembler Encoding is Artificial Neural Network encoding method. To date, Assembler Encoding has been tested in two problems, i.e. in an optimization problem in which a solution is in the form of a matrix and in the so-called predatorprey problem in which the task of ANN is to control agent-predators whose common goal is to capture a fast moving agent-prey. The next problem in which Assembler E...
متن کامل