Search
Now showing items 1-3 of 3
Novel Reinforcement Learning Algorithms and Applications to Hybrid Control Design Problems
The thesis is a compilation of two independent works.
In the first work, we develop novel weight assignment procedure, which helps us develop several schedule based algorithms. Learning the value function of a given policy ...
Average Reward Actor-Critic with Deterministic Policy Search
The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average ...
Stochastic Optimization And Its Application In Reinforcement Learning
Numerous engineering fields, such as transportation systems, manufacturing, communication networks, healthcare, and finance, frequently encounter problems requiring optimization in the presence of uncertainty. Simulation-based ...