SLAYO-RL: A Target-Driven Deep Reinforcement Learning Approach with SLAM and YoLo for an Enhanced Autonomous Agent.
José MontesTroy Costa KohwalterEsteban CluaPublished in: LARS/SBR/WRE (2023)
Keyphrases
- reinforcement learning
- autonomous agents
- multi agent
- dynamic environments
- reward signal
- learning agents
- function approximation
- reinforcement learning algorithms
- multiagent systems
- multi agent systems
- state space
- multi agent environments
- model free
- mobile robot
- markov decision processes
- rl algorithms
- control architecture
- simultaneous localization and mapping
- complex environments
- learning algorithm
- machine learning
- action selection
- partially observable domains
- optimal policy
- autonomous learning
- temporal difference
- function approximators
- policy iteration
- previously learned
- hidden state
- dynamic programming
- direct policy search
- action space
- reinforcement learning methods
- single agent
- partially observable
- optimal control