Using Deep Reinforcement Learning for Navigation in Simulated Hallways.
Gonçalo LeãoFilipe AlmeidaEmanuel TrigoHenrique FerreiraArmando SousaLuís Paulo ReisPublished in: ICARSC (2023)
Keyphrases
- reinforcement learning
- real robot
- function approximation
- learning algorithm
- state space
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- model free
- indoor environments
- deep learning
- navigation systems
- data sets
- temporal difference learning
- autonomous navigation
- learning agents
- real time
- obstacle avoidance
- temporal difference
- action selection
- optimal control
- transfer learning
- dynamic programming
- multi agent
- data mining
- neural network