Dynamic Navigation in Unconstrained Environments Using Reinforcement Learning Algorithms.
Christos ChronisGeorgios AnagnostopoulosElena PolitiGeorge DimitrakopoulosIraklis VarlamisPublished in: IEEE Access (2023)
Keyphrases
- step size
- reinforcement learning algorithms
- temporal difference
- reinforcement learning
- dynamic environments
- markov decision processes
- reinforcement learning methods
- state space
- reinforcement learning problems
- eligibility traces
- policy search
- model free
- learning algorithm
- stochastic games
- decision making
- least squares
- dynamic programming
- function approximation
- artificial neural networks