Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 22 for “"Continuous Action Space"”.

  1. Application of Deep Reinforcement Learning for Intelligent Autonomous Navigation of a Car-Like Mobile Robot

    … Learning (RL) algorithm tailored for continuous action spaces. This is achieved using Deep Deterministic Policy Gradient (DDPG), an Actor-Critic network that combines multiple cutting-edge Artificial Intelligence methods including continuous Deep-Q learning, policy gradient methods and …

    buffalo Repository record for Application of Deep Reinforcement Learning for Intelligent Autonomous Navigation of a Car-Like Mobile Robot (opens in a new tab)

  2. Deep Reinforcement Learning for Continuous Action Control

    … by combining the strong generalization and extraction ability of deep learning models with the bootstrapping nature of reinforcement learning. Many works have achieved unprecedented results, especially on discrete action control tasks. However, much less work has been done to deal with robotic …

    unsw Repository record for Deep Reinforcement Learning for Continuous Action Control (opens in a new tab)

  3. Utilizing Trajectory Optimization in the Training of Neural Network Controllers

    … Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum system, it learns an effective policy up to …

    calpoly Repository record for Utilizing Trajectory Optimization in the Training of Neural Network Controllers (opens in a new tab)

  4. Performance Enhancement of Aerial Base Stations via Reinforcement Learning-Based 3D Placement Techniques

    … the 3D location of UAV-BSs should be continuously optimized. However, solving the location optimization problem of UAV-BSs is NP-hard with no optimal solution in polynomial time for which near optimal solutions have to be exploited. Besides the conventional solutions, i.e. heuristic …

    ottawa-retro Repository record for Performance Enhancement of Aerial Base Stations via Reinforcement Learning-Based 3D Placement Techniques (opens in a new tab)

  5. Developing Reinforcement Learning Algorithms for Robots to Aim and Pour Solid Objects

    … robot can learn to pour accurately by 1) using a continuous action space, and 2) avoiding overestimation in state-action value approximation.

    usf Repository record for Developing Reinforcement Learning Algorithms for Robots to Aim and Pour Solid Objects (opens in a new tab)

  6. Reinforcement Learning with Function Approximation for Manufacturing, Operations and Maintenance of Emerging Technologies

    … making are restricted to discrete state and action spaces. Continuous control variables are typically discretized to cope with the curse of dimensionality in traditional dynamic programming methods. In this dissertation, we investigate the implementation of reinforcement learning throughout …

    houston Repository record for Reinforcement Learning with Function Approximation for Manufacturing, Operations and Maintenance of Emerging Technologies (opens in a new tab)

  7. Stackelberg Multi-Agent Reinforcement Learning for Hierarchical Environments

    … agent policies and the ability to commit to an action before the followers. These followers can observe actions taken by leaders and respond to maximize their own payoffs. Since leaders know the follower policies, they can manipulate the followers to elicit a better payoff for themselves. In …

    waterloo Repository record for Stackelberg Multi-Agent Reinforcement Learning for Hierarchical Environments (opens in a new tab)

  8. Reinforcement Learning for Parameter Control of Image-Based Applications

    … We focus on the generation of state and action space, as well as task-dependent reward. We first discuss the automatic determination of fuzzy membership functions as a specific case of the above problem. Entropy of a fuzzy event is used as a reinforcement signal. Membership functions …

    waterloo Repository record for Reinforcement Learning for Parameter Control of Image-Based Applications (opens in a new tab)

  9. Sparse Bayesian reinforcement learning

    … in hyperparameters for smart decision of action selection and filtering insignificant experience to maintain sparsity of snapshots for efficiency. The obtained memory can be used to further improve learning. First, the placement of the snapshot memories with a radial basis function kernel …

    colostate Repository record for Sparse Bayesian reinforcement learning (opens in a new tab)

  10. Toward embodied navigation through vision and language

    … a robot learns to interact with human-living spaces to perform various tasks. This thesis studies the embodied navigation problem in which a robotic agent navigates in a previously unseen indoor environment based on a challenging task. In particular, the Vision-and-Language Navigation (VLN) …

    edithcowan Repository record for Toward embodied navigation through vision and language (opens in a new tab)

  11. Bayesian State Tracking and Sim-to-Real Transfer for Vision-and-Language Navigation

    … as a sequence of expected observations and actions an agent following the correct trajectory would encounter and perform. Based on this intuition, we formulate the problem of finding the goal location in Vision-and-Language Navigation (VLN) within the framework of Bayesian state tracking -- …

    gatech Repository record for Bayesian State Tracking and Sim-to-Real Transfer for Vision-and-Language Navigation (opens in a new tab)

  12. Data-driven design for multihop and multi-band cellular networks

    … as a Markov decision process (MDP) with a continuous action space and solve it using the deep deterministic policy gradient (DDPG) algorithm. Detailed system-level simulations show that the reinforcement learning RL-based scheduler can reduce the mean delay by 230% and 260% compared to a …

    texas Repository record for Data-driven design for multihop and multi-band cellular networks (opens in a new tab)

  13. Cooperation and communication in multiagent deep reinforcement learning

    … machine learning concerned with learning which actions to execute in an unknown environment in order to maximize cumulative reward. As agents begin to perform tasks of genuine interest to humans, they will be faced with environments too complex for humans to predetermine the correct actions …

    texas Repository record for Cooperation and communication in multiagent deep reinforcement learning (opens in a new tab)

  14. Reinforcement Learning for Shared Autonomy in Powered Wheelchair Navigation

    … using deep reinforcement learning within a continuous action space, which lifts the reliance on the aforementioned assumptions. Initially, a reinforcement learning agent is developed to autonomously navigate complex indoor environments without the need for a map. The agent is trained using a …

    kent Download PDF for Reinforcement Learning for Shared Autonomy in Powered Wheelchair Navigation (opens in a new tab)

  15. Sensorimotor Aspects of Brain Function: Development, Internal Dynamics, and Tool Use

    … body by developing a cortical map of its motor actions?; (2) How can predictive internal brain dynamics play an important role in external behavior (authorship of actions)?; (3) How tool-use emerges in a sensorimotor system interacting with the environment? The first topic considers developing a …

    tamu Repository record for Sensorimotor Aspects of Brain Function: Development, Internal Dynamics, and Tool Use (opens in a new tab)

  16. A combined mechanism for UAV explorative path planning, task allocation and predictive placement

    … first responder personnel, and to ensure action can be taken by the UAVs quickly, co-operatively, and with close to optimal results. Key to this work, is the idea of enabling coordinated UAVs to explore a disaster space to discover incidents and then to allow more detailed examination, …

    soton Download PDF for A combined mechanism for UAV explorative path planning, task allocation and predictive placement (opens in a new tab)

  17. Learning-based Motion Planning for High-DoF Robot Systems

    … as it entails a multitude of context-dependent actions to complete the task. Our objective is to replicate a reference image using brush strokes, with the goal encoded through observations. We will focus on how to address the sparse reward distribution with a large continuous action space. …

    maryland Repository record for Learning-based Motion Planning for High-DoF Robot Systems (opens in a new tab)

  18. Downhole Intelligence for Drilling Systems Using Supervised and Deep Reinforcement Learning Techniques

    … solutions are not tractable because of the continuous action space for steering, possible observations within each sequence, and the computational demands of simulating updated environment. Function approximators are used in a policy gradient approach utilizing an advanced technique of …

    tamu Repository record for Downhole Intelligence for Drilling Systems Using Supervised and Deep Reinforcement Learning Techniques (opens in a new tab)

  19. Learning in Engineered Multi-agent Systems

    … produced by a wind farm. Due to aerodynamic interactions between wind turbines, each turbine maximizing its individual power--as is the case in present-day wind farms--does not lead to optimal farm-level power capture. Further, there are no good models to capture the said aerodynamic interactions, …

    maryland Repository record for Learning in Engineered Multi-agent Systems (opens in a new tab)

Page 1 of 2