The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this work, we present a network architecture to solve a supervised learning problem, the classification of a handwritten dataset, and a reinforcement learning problem, a complex First-Person Shooter 3D game environment. We used a Deep Neural Network model to solve both problems. For classification, we used a Softmax regression and cross entropy loss to train the network. To play the game, we used...
Urban traffic flow is dynamic and uncertain. In this paper, we combine the deep learning and the reinforcement learning, and design an intersection signal controller based on Q-learning and convolutional neural network. We redefine the state space and the reward function. The training and simulation of the controller are carried out in traffic micro-simulator SUMO. Compared with timing control, the...
Recently, a state-of-the-art algorithm, called deep deterministic policy gradient (DDPG), has achieved good performance in many continuous control tasks in the MuJoCo simulator. To further improve the efficiency of the experience replay mechanism in DDPG and thus speeding up the training process, in this paper, a prioritized experience replay method is proposed for the DDPG algorithm, where prioritized...
Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without...
This paper investigates the potential of combining deep learning and neuroevolution to create a bot for a simple first person shooter (FPS) game capable of aiming and shooting based on high-dimensional raw pixel input. The deep learning component is responsible for visual recognition and translating raw pixels to compact feature representations, while the evolving network takes those features as inputs...
Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in deep neural networks have substantially improved the performance of this task. Most state-of-the-art approaches follow an encoder-decoder framework, which generates captions using a sequential recurrent prediction model. However,...
This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences...
Increase in popularity of deep convolutional neural networks in many different areas leads to increase in the use of these networks in reinforcement learning. Training a huge deep neural network structure by using simple gradient descent learning can take quite a long time. Some additional learning approaches should be utilized to solve this problem. One of these techniques is use of momentum which...
In this work a novel approach to Transfer Learning for the use in Deep Reinforcement Learning is introduced. The agent is realized as an actor-critic framework, namely the Deep Deterministic Policy Gradient algorithm. The Q-function and the policy are represented as deep feed-forward networks, that are trained by minimizing the mean squared Bellman error and by maximizing the expected reward, respectively...
The aim of this paper is to solve the control problem of trajectory tracking of Autonomous Underwater Vehicles (AUVs) through using and improving deep reinforcement learning (DRL). The deep reinforcement learning of an underwater motion control system is composed of two neural networks: one network selects action and the other evaluates whether the selected action is accurate, and they modify themselves...
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space...
Artificial intelligence (AI) agent created with Deep Q-Networks (DQN) can defeat human agents in video games. Despite its high performance, DQN often exhibits odd behaviors, which could be immersion-breaking against the purpose of creating game AI. Moreover, DQN is capable of reacting to the game environment much faster than humans, making itself invincible (thus not fun to play with) in certain types...
Obstacle avoidance is one of the most important problems in autonomous robots. This paper suggests a collision avoidance system using reinforcement learning. Hand-crafted features are used to approximate Q value. With off-line learning, we develop a general collision avoidance system and use this system to unknown environment. Simulation results show that our mobile robot agent using reinforcement...
Policy search can in principle acquire complex strategies for control of robots and other autonomous systems. When the policy is trained to process raw sensory inputs, such as images and depth maps, it can also acquire a strategy that combines perception and control. However, effectively processing such complex inputs requires an expressive policy class, such as a large neural network. These high-dimensional...
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without extensive manual engineering. However, robotic skill learning must typically make trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human demonstrations, instrumentation of the training...
Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy...
Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems due to large search spaces. This paper proposes a three-stage method for multi-domain dialogue policy learning-termed NDQN, and applies it to an information-seeking spoken dialogue system in the domains of restaurants and hotels. In this method, the first stage does multi-policy...
Neural networks are a powerful function approximation tool which has the ability to model any function with arbitrary precision. For any function as a black box, it is able to reconstruct the function given the target and the input data. However, there are problems where the target is at least partially unknown. In such cases it is impossible for a traditional neural network to compute the gradient...
Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy...
Due to its ability to learn complex behaviors in high-dimensional state-action spaces, deep reinforcement learning algorithms have attracted much interest in the robotics community. For a practical reinforcement learning implementation on a robot, it has to be provided with an informative reward signal that makes it easy to discriminate the values of nearby states. To address this issue, prior information,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.