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 307 for “"Policy Optimization"”.

  1. Evolutionary Policy Optimization

    … trade-off without sacrificing sample efficiency. Policy gradient (PG) methods excel in exploitation through fine-grained, gradient-based optimization but often struggle with exploration due to their focus on local search. In contrast, evolutionary computation (EC) methods excel in global …

    texas Repository record for Evolutionary Policy Optimization (opens in a new tab)

  2. Proximal Policy Optimization in StarCraft

    … which have some of the benefits of trust region policy optimization (TRPO), but it is much simpler to implement, more general for environment, and have better sample complexity. The StarCraft environment: Blood War Application Programming Interface (BWAPI) is open source to test. The results show …

    unt Repository record for Proximal Policy Optimization in StarCraft (opens in a new tab)

  3. Koopman-Inspired Proximal Policy Optimization (KIPPO)

    … dynamics remains a challenge, particularly for policy gradient methods. These methods often struggle due to high-variance in gradient estimates, non-convex optimization landscapes, and sample inefficiency, resulting in unstable learning, suboptimal policies, and trade-offs between performance …

    ut-knoxville Repository record for Koopman-Inspired Proximal Policy Optimization (KIPPO) (opens in a new tab)

  4. Policy Optimization with f-Divergence Regularization

    Policy iteration is a common algorithm framework in reinforcement learning (RL) to find the optimal policy for a Markov decision process (MDP). Previously, researchers have developed several policy iteration algorithms based on the Kullback–Leibler (KL) divergence. In this thesis, we extend …

    carleton Repository record for Policy Optimization with f-Divergence Regularization (opens in a new tab)

  5. Critic-derived shaping in Proximal Policy Optimization

    The simplicity and stability of Proximal Policy Optimization (PPO) in reinforcement learning make it popular, yet its on-policy training loop may be sample-inefficient. This thesis investigates whether PPO can leverage temporal-difference (TD) error, a signal that it already computes, in a …

    ubc Repository record for Critic-derived shaping in Proximal Policy Optimization (opens in a new tab) Download PDF for Critic-derived shaping in Proximal Policy Optimization (opens in a new tab)

  6. Preferential proximal policy optimization in reinforcement learning

    The Proximal Policy Optimization (PPO), a policy gradient method, excels in reinforcement learning with its ”surrogate” objective function and stochastic gradient ascent. However, PPO does not fully consider the significance of frequently encountered states in policy/value updates. To address this, …

    uoit Repository record for Preferential proximal policy optimization in reinforcement learning (opens in a new tab)

  7. Proximal Policy Optimization for Radiation Source Search

    … of DRL known as stochastic, model-free, on-policy gradients that learns strictly through interaction with an environment to develop a useful policy for a specified goal. A novel neural network architecture (RAD-A2C) based on the actor critic (A2C) framework that uses a gated recurrent unit …

    portland-state Repository record for Proximal Policy Optimization for Radiation Source Search (opens in a new tab)

  8. Efficient trajectory and policy optimization using dynamics models

    … on a central problem in robotics: trajectory and policy optimization. We develop new algorithmic and theoretic foundations of (1) computationally efficient trajectory optimization and (2) unbiased sample efficient policy optimization. Our research increases the practicality of continuous-time …

    gatech Repository record for Efficient trajectory and policy optimization using dynamics models (opens in a new tab)

  9. Essays on Tax Policy Optimization under Heterogeneous Treatment Effects

    … is difficult, with direct implications for tax policy in developing countries.</p>

    duke Repository record for Essays on Tax Policy Optimization under Heterogeneous Treatment Effects (opens in a new tab)

  10. Policy optimization for industrial benchmark using deep reinforcement learning

    Significant advancements have been made in the field of Reinforcement Learning (RL) in recent decades. Numerous novel RL environments and algorithms are mastering these problems that have been studied, evaluated, and published. The most popular RL benchmark environments produced by OpenAI Gym and …

    colostate Repository record for Policy optimization for industrial benchmark using deep reinforcement learning (opens in a new tab)

  11. Sensor interceptor operational policy optimization for maritime interdiction missions

    … method of producing an optimal decision policy for the interdiction force is presented in this thesis, it is shown that such computation is intractable. The models developed in this study are used to analyze and evaluate the performance of a heuristic decision policy that we recommend to …

    nps Repository record for Sensor interceptor operational policy optimization for maritime interdiction missions (opens in a new tab)

  12. Designing policy optimization algorithms for multi-agent reinforcement learning

    … algorithms essentially solve a bi-level optimization problem by tracking an artificial auxiliary variable in addition to the decision variable and updating them at different rates. We propose a two-time-scale stochastic gradient descent method under a special type of gradient oracle which …

    gatech Repository record for Designing policy optimization algorithms for multi-agent reinforcement learning (opens in a new tab)

  13. Autonomous Excavation Using Reinforcement Learning with Proximal Policy Optimization

    … hydraulic controller was trained using proximal policy optimization. Together with the hydraulic controller, a PID was implemented as a positional controller for a complete system capable of performing grading tasks. Training was conducted by testing different reward functions and parameter …

    chalmers Repository record for Autonomous Excavation Using Reinforcement Learning with Proximal Policy Optimization (opens in a new tab)

  14. EFFECTIVENESS OF PROXIMAL POLICY OPTIMIZATION METHODS FOR NEURAL PROGRAM INDUCTION

    … reinforcement learning based on standard policy gradient methods as a mechanism for performing neural program induction. In this thesis, I modified NVM-RL using one of the most popular reinforcement learning algorithms, proximal policy optimization (PPO). Surprisingly, using PPO with the …

    maryland Repository record for EFFECTIVENESS OF PROXIMAL POLICY OPTIMIZATION METHODS FOR NEURAL PROGRAM INDUCTION (opens in a new tab)

  15. Learning-based optimal and robust control: A policy optimization perspective

    … robotic tasks. Central to this success is policy optimization (PO), a subclass of RL where policies—parameterized mappings from observations to actions—are iteratively optimized to enhance system performance. PO’s flexibility, scalability, and data-driven nature make it effective for …

    uiuc Repository record for Learning-based optimal and robust control: A policy optimization perspective (opens in a new tab)

  16. Taking advantage of common assumptions in policy optimization and reinforcement learning

    … using simulated environments via gradient-based optimization methods. It begins by investigating the effects that complex model classes have on settings where a policy is learned through the imitation of expert data which is gathered through repeated environmental interaction. Next, it discusses …

    ubc Repository record for Taking advantage of common assumptions in policy optimization and reinforcement learning (opens in a new tab) Download PDF for Taking advantage of common assumptions in policy optimization and reinforcement learning (opens in a new tab)

  17. A systems analysis formulation and criteria determination for ship maintenance policy optimization

    … To formulate the warship maintenance optimization problem a general background of the Navy's maintenance system is given and from this description annual operation and maintenance cost emerges as a valid criterion for judging alternative maintenance policies. A discussion of dependent …

    nps Repository record for A systems analysis formulation and criteria determination for ship maintenance policy optimization (opens in a new tab)

  18. World model based multi-agent proximal policy optimization framework for multi-agent pathfinding

    … communication block into a multi-agent proximal policy optimization framework. The evaluation is conducted in a simulation based environment, featuring continuous state and action spaces. The simulator consists of a vectorized 2D physics engine where agents are bound by the laws of physics. …

    uvic Repository record for World model based multi-agent proximal policy optimization framework for multi-agent pathfinding (opens in a new tab)

  19. The Impact Of Experience Replay Buffers On Catastrophic Forgetting Within Proximal Policy Optimization

    Catastrophic Forgetting continues to be a prevalent issue for any neural-based approach to learning. Without better understanding and solutions to solving catastrophic forgetting, learning performance and efficacy in autonomous agents, particularly deep learning-based agents will become drastically …

    ucf Repository record for The Impact Of Experience Replay Buffers On Catastrophic Forgetting Within Proximal Policy Optimization (opens in a new tab)

Page 1 of 16