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 70 for “"Soft Actor-Critic"”.

  1. Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving

    … enough to converge. Among DRL algorithms, Soft Actor-Critic (SAC) is a powerful method capable of handling complex and continuous state-action spaces. However, long training time and data efficiency are the main drawbacks of this algorithm, even though SAC is robust for complex and dynamic …

    tamu Repository record for Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving (opens in a new tab)

  2. Curriculum-based soft actor-critic for multi-section roll-to-roll tension control

    … change. This thesis presents a curriculum-based Soft Actor-Critic (SAC) approach for learning adaptive tension control policies that generalize across diverse operating conditions. The proposed method formulates R2R tension control as a Markov Decision Process and employs a three-phase curriculum …

    texas Repository record for Curriculum-based soft actor-critic for multi-section roll-to-roll tension control (opens in a new tab)

  3. Reinforcement learning of a feedforward controller with soft actor-critic for a reaching task

    … learning. Additionally, we investigate how the factors such as the difficulty of the task and noise present in the motor system are related to human motor control. Hence, a one-dimensional muscle-based biomechanical model is built to create a reaching task setup. The model contains an actuator …

    ubc Repository record for Reinforcement learning of a feedforward controller with soft actor-critic for a reaching task (opens in a new tab) Download PDF for Reinforcement learning of a feedforward controller with soft actor-critic for a reaching task (opens in a new tab)

  4. Constrained hybrid soft actor–critic (CH-SAC) with a mobility-and load-aware fusion predictor

    … signals are integrated into a Constrained Hybrid Soft Actor–Critic (CH-SAC) controller supported by a guard mechanism that monitors queue pressure, utilisation, latency spikes, and drop ratio. The framework is evaluated using real mobility traces from the Beijing T-Drive dataset in both a …

    ets-quebec Download PDF for Constrained hybrid soft actor–critic (CH-SAC) with a mobility-and load-aware fusion predictor (opens in a new tab)

  5. Reinforcement Learning Application in Wavefront Sensorless Adaptive Optics System

    … off-policy reinforcement learning framework, the soft actor-critic, in the adaptive optics system controller. This integration results in a model-free online controller capable of mitigating wavefront distortion. The soft actor-critic controller processes the acquired data matrix from the …

    ottawa-retro Repository record for Reinforcement Learning Application in Wavefront Sensorless Adaptive Optics System (opens in a new tab)

  6. Learning-Based Controller for Aerial Robotics

    … (SARL) approach and trained our agent using the Soft Actor-Critic (SAC) algorithm, renowned for its strong exploratory capabilities and stability in learning. For training and simulation, we utilized the Gym-PyBullet-Drone environment due to its versatility and ease of integration, enabling …

    houston Repository record for Learning-Based Controller for Aerial Robotics (opens in a new tab) Embargoed until 2026-12-01

  7. Data Driven Turbine Control in Tidal Power Generation: Development and comparison of data driven turbine control algorithms in a simulated underwater kite environment

    … deep reinforcement learning algorithm Soft Actor-Critic. The solution also incorporates pre-training on generated data to validate a possible simulation-to-reality adaptation. Within the adopted simulation setting, the main finding is that predictive turbine control based on forecasted …

    chalmers Repository record for Data Driven Turbine Control in Tidal Power Generation: Development and comparison of data driven turbine control algorithms in a simulated underwater kite environment (opens in a new tab)

  8. Learning optimal sampling policies for sketching of huge data matrices

    … are used for TSGPR-SketchyCoreSVD, and Soft Actor-Critic is applied to SAC-SketchyCoreSVD. Experiments show TSGPR-SketchyCoreSVD actively learns the subsampling policy and produces higher accuracy than the original SketchyCoreSVD. SAC-SketchyCoreSVD is still developing, but its …

    texas Repository record for Learning optimal sampling policies for sketching of huge data matrices (opens in a new tab)

  9. Reinforcement learning tuning of sliding mode control for an underactuated autonomous surface vehicle

    … the robustness of sliding mode control. Soft Actor Critic (SAC) and Proximal Policy Optimization (PPO) algorithms are both used to compare the training of RL agents to estimate the required controller parameters. The system is implemented and evaluated in a MATLAB/Simulink environment …

    texas Repository record for Reinforcement learning tuning of sliding mode control for an underactuated autonomous surface vehicle (opens in a new tab)

  10. Posilované učení pro pohyb robota

    … Jedním z relativně nových řešení je algoritmus Soft Actor-Critic (SAC), který se objevil současně s podobně performním TD3, a oba překonávají starší DDPG. Agent SAC je odměňován za více náhodné chování, jeho cílem je tedy kromě maximalizace odměny také maximalizace entropie. Tato práce ukazuje …

    brno-tech Repository record for Posilované učení pro pohyb robota (opens in a new tab)

  11. Gilusis skatinamasis mokymas vertybinių popierių portfeliui optimizuoti /

    … Gradient (DDPG), Twin Delayed DDPG (TD3) and Soft Actor Critic (SAC). In chapter 5, we propose software program for analysing automated stock trading using deep reinformecent learning techniques. We train a deep reinforcement learning models to optimize a stock portfolio containing 30 Dow …

    vilnius Repository record for Gilusis skatinamasis mokymas vertybinių popierių portfeliui optimizuoti / (opens in a new tab)

  12. SCALEX: SCALability EXploration of multi-agent reinforcement learning agents in grid-interactive efficient buildings

    … unclear. This thesis examines the scalability of Soft-Actor Critic (SAC) in multi-agent systems, comparing decentralized-independent SACs and centralized SACs using CityLearn, an OpenAI Gym environment. We consider neighborhoods consisting of 2 to 64 single-family residential buildings, each …

    texas Repository record for SCALEX: SCALability EXploration of multi-agent reinforcement learning agents in grid-interactive efficient buildings (opens in a new tab)

  13. A Comprehensive Study on Energy Management Strategy Design of an Extended-Range Electric Vehicle

    … health. The comparative results show that the Soft Actor-Critic (SAC) had a 36% faster convergence speed than a traditional algorithm while providing a smoother and more stable action space. The fuel consumption with SAC also outplays by around 3%, which achieves almost 90% of the DP results.

    uts Repository record for A Comprehensive Study on Energy Management Strategy Design of an Extended-Range Electric Vehicle (opens in a new tab)

  14. Autonomous Navigation In Real-Time Endovascular Simulation

    … endovascular environment. Specifically, a Soft Actor-Critic (SAC) algorithm is employed to train an agent to control a micro guidewire and a micro catheter for path-following tasks. The simulation environment is based on the VIST simulator, where the agent observes a 23-dimensional state …

    chalmers Repository record for Autonomous Navigation In Real-Time Endovascular Simulation (opens in a new tab)

  15. Autonomous Navigation In Real-Time Endovascular Simulation

    … endovascular environment. Specifically, a Soft Actor-Critic (SAC) algorithm is employed to train an agent to control a micro guidewire and a micro catheter for path-following tasks. The simulation environment is based on the VIST simulator, where the agent observes a 23-dimensional state …

    chalmers Repository record for Autonomous Navigation In Real-Time Endovascular Simulation (opens in a new tab)

  16. Machine Learning-Based Resource Scheduling and Link Adaptation in Massive MIMO Networks

    … beamforming can achieve. As such, it is critical for the base station to schedule a suitable group of users in each time and frequency resource block to achieve maximum spectral efficiency while adhering to fairness constraints among the users. Additionally, in dynamic wireless …

    rice Repository record for Machine Learning-Based Resource Scheduling and Link Adaptation in Massive MIMO Networks (opens in a new tab)

  17. Combining Supervised Pretraining and Reinforcement Learning for Scalable Low-Thrust Trajectory Design

    … that populate the experience replay buffer of a Soft Actor-Critic (SAC) agent. Comparative experiments against a baseline SAC agent trained from scratch show improvements in average episode reward and higher-performing controllers when using pretraining in Monte Carlo validation tests. These …

    maryland Repository record for Combining Supervised Pretraining and Reinforcement Learning for Scalable Low-Thrust Trajectory Design (opens in a new tab)

  18. Risk Prediction and Treatment Identification for Reducing the Risk of Adverse Outcomes in Mental Health

    … to explore the data and identify AMH-related factors associated with adverse outcomes, defined as first healthcare encounters indicating homelessness or interactions with police. Second, it compares various data preprocessing methods, including event-based and matrix-based sequence …

    calgary Repository record for Risk Prediction and Treatment Identification for Reducing the Risk of Adverse Outcomes in Mental Health (opens in a new tab)

  19. A Safe Reinforcement Learning Approach for Energy Efficient Federated Learning in Wireless Communication Networks

    … ΤΝ. Προς αυτόν τον σκοπό, προτείνεται η λύση του Soft Actor Critic (SAC) Ενισχυτικής Μάθησης (ΕΜ) που στοχεύει στην ελαχιστοποίηση της συνολικής κατανάλωσης ενέργειας μίας τεχνολογίας ΟΜ. Η αποτελεσματικότητα της προτεινόμενης μεθόδου παρουσιάζεται με αποτελέσματα που συγκρίνονται με τρεις …

    athens Repository record for A Safe Reinforcement Learning Approach for Energy Efficient Federated Learning in Wireless Communication Networks (opens in a new tab)

Page 1 of 4