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 253 for “"policy gradient"”.
-
Policy gradient methods for linear quadratic problems
… results on the theoretical convergence of policy gradient methods, which are the basis of many reinforcement learning algorithms, in both single-agent and multi-agent linear quadratic problems.</p> <p>In the single-agent setting, we show the global convergence of such methods to the optimal …
-
Policy Gradient Methods: Variance Reduction and Stochastic Convergence
… learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies, and using a policy from the class, and a trajectory through the environment taken by the agent using this …
-
APPLYING POLICY GRADIENT METHODS TO OPEN-ENDED DOMAINS
… key implementation details, it explores why policy gradient methods alone are insufficient for sparse-reward tasks. These findings motivate the use of curriculum learning to decompose problems into learnable subtasks and to prioritize learnable objectives. Building on these insights, this …
-
Policy-Gradient Algorithms for Partially Observable Markov Decision Processes
… One such class of algorithms are the so-called policy-gradient methods from reinforcement learning. They seek to adjust the parameters of an agent in the direction that maximises the long-term average of a reward signal. Policy-gradient methods are attractive as a \emph{scalable} approach for …
-
Reinforcement Learning Policy Gradient Methods for Reservoir Operation Management and Control
… are among issues that water managers and policymakers face on a regular basis. These concerns have sparked interest in applying different techniques to determine reservoir operation policy and improve reservoir release decisions. As the resolution of the analysis rises, it becomes more …
-
Reimagining Exploration: Theoretical Insights and Practical Advancements in Policy Gradient Methods
In reinforcement learning, direct policy optimization, and specifically policy gradient methods, has proven effective for solving complex control problems. However, these methods are highly sensitive to the evolution of the policy's stochasticity during learning. It is essential to maintain …
-
Reinforcement Learning: Applying Low Discrepancy Action Selection to Deep Deterministic Policy Gradient
Reinforcement learning (RL) is a subfield of machine learning concerned with agents learning to behave optimally by interacting with an environment. One of the most important topics in RL is how the agent should explore, that is, how to choose actions in order to rate their impact on long-term …
-
Risk-Averse Policy Gradient for Tail Risk Optimization Using Extreme Value Theory
In this work, we develop a risk-averse Policy Gradient algorithm in a tail risk optimization problem. Our objective is to find the optimal policy that minimizes tail risk, given a risk measure such as Conditional Value at Risk (CVaR). We employed Extreme Value Theory, along with the automated …
-
Evalutating Multi-Agent Policy Gradient Methods for Resource Allocation in C-V2X Networks
… a unified evaluation framework for multi-agent policy gradient methods in C-V2X highway environments. A realistic system model is constructed with standardized channel dynamics, queueing behavior, and time-scale control. Three benchmark task families, NFIG, SIG, and POSIG, are introduced to vary …
-
Sample Complexity of Incremental Policy Gradient Methods for Solving Multi-Task Reinforcement Learning
… this problem, we are interested in studying the gradient approach, which iteratively updates an estimate of the optimal policy using the gradients of the value functions. The classic policy gradient method, however, may be expensive to implement in the multi-task settings as it requires access to …
-
Deep deterministic policy gradient: applications in process control and integrated process design and control
… a RL algorithm referred to as Deep Deterministic Policy Gradient (DDPG) to two typical areas of process operations in chemical engineering, i.e., process control and process design and control. Parametric uncertainty and disturbances are considered in both approaches (i.e., process control and …
-
OFFLINE REINFORCEMENT LEARNING FOR MDPS AND CONFOUNDED POMDPS: POLICY GRADIENT ALGORITHMS AND PESSIMISTIC MODEL-BASED APPROACHES
… practical implementations or restrict the policy space, limiting the potential of model-based methods. To address this, we propose MoMA, a model-based mirror ascent algorithm with general function approximations under partial offline data coverage. Unlike previous methods, MoMA utilizes an …
-
Adaptive Model-Free Control Applied to Truck Front Wheel Drive: Real time control with reinforcement learning utilising recurrent deterministic policy gradient
… learning method “Recurrent Deterministic Policy Gradients” (RDPG) is then modified to work continuously in real time and implemented to improve the performance of the network and make it adaptive. The emulating network performed similarly, albeit somewhat worse, compared to the original …
-
Reinforcement Learning in Linear Quadratic Deep Structured Teams with Performance Guarantee
… global convergence of model-based and model-free gradient descent and natural policy gradient descent algorithms is studied for a class of linear quadratic deep structured teams. In such systems, agents are partitioned into a few sub populations wherein the agents in each sub-population are …
-
DEEP REINFORCEMENT LEARNING-BASED APPROACHES FOR SCATTERED STORAGE ASSIGNMENT AND BATCH PICKING OPTIMIZATION IN A MODERN WAREHOUSE
… Advantaged Actor-Critic with Natural Beta policy gradient, Proximal Policy Optimization with Natural Beta policy gradient, and Phasic Policy Gradient with Natural Beta policy gradient, are designed to learn the weights of the demand and correlation factors. The third work of this thesis …
-
Convergence to Nash in the potential Linear Quadratic games and accelerated learning in games
… (LQ) games, we also study the convergence of the policy gradient algorithms, a class of conventional reinforcement learning methods. LQ games have applications in engineering. It has been shown that using policy gradient algorithms by agents does not guarantee convergence to the Nash equilibrium. …
Page 1 of 13