A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
We study a primal-dual reinforcement learning (RL) algorithm for the online constrained
Markov decision processes (CMDP) problem, wherein the agent explores an optimal policy …
Markov decision processes (CMDP) problem, wherein the agent explores an optimal policy …
Trajectory Planning for Autonomous Vehicle Using Iterative Reward Prediction in Reinforcement Learning
H Park - arXiv preprint arXiv:2404.12079, 2024 - arxiv.org
Traditional trajectory planning methods for autonomous vehicles have several limitations.
Heuristic and explicit simple rules make trajectory lack generality and complex motion. One …
Heuristic and explicit simple rules make trajectory lack generality and complex motion. One …
A Rule-Compliance Path Planner for Lane-Merge Scenarios Based on Responsibility-Sensitive Safety
Lane merging is one of the critical tasks for self-driving cars, and how to perform lane-merge
maneuvers effectively and safely has become one of the important standards in measuring …
maneuvers effectively and safely has become one of the important standards in measuring …
Neuro-symbolic deep reinforcement learning for safe urban driving using low-cost sensors.
M Albilani - 2024 - theses.hal.science
The research conducted in this thesis is centered on the domain of safe urban driving,
employing sensor fusion and reinforcement learning methodologies for the perception and …
employing sensor fusion and reinforcement learning methodologies for the perception and …