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 18 of 18 for “"critic network"”.

  1. Foundations of Whatifiness: Asking Counterfactual What if? Questions through Quantum Principles for Adaptive Decision-making

    … Our technique employs an on-policy actor-critic model in which the quantum layer of the actor network is based on a tree tensor network circuit, while the critic network is constructed according to a classical-quantum hybrid transformer model with quantum self-attention layers. …

    carleton Repository record for Foundations of Whatifiness: Asking Counterfactual What if? Questions through Quantum Principles for Adaptive Decision-making (opens in a new tab)

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

    … 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 actor-critic networks. A combination of two separate feedforward neural networks with Rectified …

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

  3. Deep Learning Framework for Graph-Based Molecular Drug Discovery

    … framework, which combines Graph Convolutional Networks (GCN), Generative Adversarial Networks (GAN), and Federated Learning (FL) to generate novel molecules while preserving data privacy. FL allows learning from distributed clients without sharing local datasets, GCN extracts molecular …

    unm Repository record for Deep Learning Framework for Graph-Based Molecular Drug Discovery (opens in a new tab)

  4. Online Adaptive Model-Free MIMO Control of Lighter-Than-Air Dirigible Airship

    … a single layer, partially connected neural network is formulated as a value function appropriator in accordance with Weierstrass higher-order approximation theorem. The so-called critic-network is updated using gradient descent methods on the mean-squared error of the temporal difference …

    ottawa-retro Repository record for Online Adaptive Model-Free MIMO Control of Lighter-Than-Air Dirigible Airship (opens in a new tab)

  5. Robust actor-critic trajectory optimization and Autonomous harvesting robot integration

    … into two parts. First, we develop a neural network–based constrained trajectory optimization algorithm with stability guarantees, along with a neural network–driven numerical error correction. The framework reformulates the structure of an optimal control problem as a neural network …

    ucf Repository record for Robust actor-critic trajectory optimization and Autonomous harvesting robot integration (opens in a new tab)

  6. Deep Learning for Multiple Unmanned Aerial Vehicle Coordination in Air Corridors

    … uniform format for processing by the deep actor-critic network. Additionally, HTransRL employs curriculum learning to enhance training efficiency. When implementing HTransRL in real-world applications, it must adapt to disturbances like wind perturbations. To address this challenge, we …

    unm Repository record for Deep Learning for Multiple Unmanned Aerial Vehicle Coordination in Air Corridors (opens in a new tab)

  7. Exploration of an unknown space by collective robotics using fuzzy logic and reinforcement learning

    … leaming. A simple ACD uses two neural networks, e.g., a criticand an action (control) network. The critic network leams to predict the total fiiture cost from a given environment to the terminal state, while the action network leams a policy function to optimize critic's cost output at …

    ttu Repository record for Exploration of an unknown space by collective robotics using fuzzy logic and reinforcement learning (opens in a new tab)

  8. A reinforcement learning-based approach for adaptive real-time sensor data denoising in mining operations

    … real-time updates to these models are critical, as sensor data plays a vital role in characterizing deposit properties. However, noise often affects sensor measurements, compromising the accuracy and reliability of resource models. This study presents a novel reinforcement learning (RL) …

    mtu Repository record for A reinforcement learning-based approach for adaptive real-time sensor data denoising in mining operations (opens in a new tab)

  9. Advances to forecasting and planning frameworks toward resilient power distribution systems

    … computational cost. The goal is to ensure that critical facilities in a PDS that depend on electricity remain energized or can recover when impacted by severe wind events. To predict DER adoption, this dissertation develops a hybrid forecasting model that combines exponential smoothing, …

    iastate Repository record for Advances to forecasting and planning frameworks toward resilient power distribution systems (opens in a new tab)

  10. Trajectory Tracking Control of Unmanned Ground Vehicles using an Intermittent Learning Algorithm

    … is model-free, a Q-learning setup with an actor-network to approximate the optimal intermittent controller and a critic network to approximate the optimal cost, resulting in the appropriate tuning laws is considered.

    vt Repository record for Trajectory Tracking Control of Unmanned Ground Vehicles using an Intermittent Learning Algorithm (opens in a new tab)

  11. NLP Analysis in the Intersection of RLHF and NER

    … into the NER framework. By using an actor-critic Re- inforcement Learning paradigm, the model continuously improves recognition through iterative feedback and reward-based mechanisms. The proposed system employs GloVe embeddings to capture contextual word representations, look after a …

    ttu Repository record for NLP Analysis in the Intersection of RLHF and NER (opens in a new tab)

  12. Multi-agent reinforcement learning for the coordination of residential energy flexibility

    … and flexible household loads in a distribution network. Additionally, a generative adversarial network-based data generator is developed to obtain realistic training and testing data. Experiments conducted in this environment showed that standard independent learners fail to coordinate in the …

    oxford Repository record for Multi-agent reinforcement learning for the coordination of residential energy flexibility (opens in a new tab)

  13. Knowledge-Guided Deep Reinforcement Learning for Interactive Recommendation

    … by the recent advance in Graph Convolutional Network and the knowledge-aware recommendation, we design a Knowledge-Guided deep Reinforcement learning (KGRL) model to harness the advantages of both reinforcement learning and knowledge graphs for the interactive recommendation. This model is …

    unsw Repository record for Knowledge-Guided Deep Reinforcement Learning for Interactive Recommendation (opens in a new tab)

  14. Hardware-Efficient Scalable Reinforcement Learning Systems

    … function approximators, such as arti…cial neural networks.</p> <p>This dissertation focuses on practical methodologies for solving reinforcement learning problems with large state and/or action spaces. In particular, the work addresses scenarios in which an agent does not have full knowledge of …

    utk-theses Repository record for Hardware-Efficient Scalable Reinforcement Learning Systems (opens in a new tab)

  15. Learning-based Physics Simulation with Collision Handling

    … algorithms that leverage the benefits of neural networks and optimization techniques. We use neural networks to compress high-dimensional 3D deformable models and accelerate the processing time. We also employ algorithms such as reinforcement learning, active learning, and imitation learning to …

    maryland Repository record for Learning-based Physics Simulation with Collision Handling (opens in a new tab)

  16. Frequency and Voltage Control of Islanded Microgrids

    … self-sustainability of future distribution networks and to provide energy for remote communities. In order to have a stable system, both primary and secondary frequency and voltage control of the MG are critical. From a primary control perspective, it is essential to maintain frequency and …

    waterloo Repository record for Frequency and Voltage Control of Islanded Microgrids (opens in a new tab)

  17. MODEL-BASED REINFORCEMENT LEARNING FOR COMPLEX ENVIRONMENTS

    … interacting keypoints and learns a graph neural network that captures abstractly the geometry and interaction dynamics of the keypoints. Such a parameterization tackles the high DoF problem and complex non-linear dynamics issue of a deformable object. We train a recurrent graph dynamics, which …

    nus Repository record for MODEL-BASED REINFORCEMENT LEARNING FOR COMPLEX ENVIRONMENTS (opens in a new tab) Download file for MODEL-BASED REINFORCEMENT LEARNING FOR COMPLEX ENVIRONMENTS (opens in a new tab)

  18. Artificial intelligence-empowered resource management system for fog computing networks

    … is expanding rapidly and advancing in terms of networking technologies. The rapid increase wireless services and applications is demanding faster and higher-capacity networks. Additionally, the Internet-of-Things (IoT) is fueling the need for massive device connectivity and ultra-reliable and …

    ets-quebec Download PDF for Artificial intelligence-empowered resource management system for fog computing networks (opens in a new tab)