A new approach for drone tracking with drone using Proximal Policy Optimization based distributed deep reinforcement learning.
Ziya TanMehmet KarakösePublished in: SoftwareX (2023)
Keyphrases
- reinforcement learning
- optimal policy
- multi agent
- policy search
- distributed systems
- action selection
- camera network
- real time
- cooperative
- state space
- function approximation
- optimization problems
- markov decision process
- mobile agents
- object tracking
- global optimization
- distributed environment
- approximate dynamic programming
- control policies
- reinforcement learning problems
- kalman filter
- optimization algorithm
- particle filter
- peer to peer
- reinforcement learning algorithms
- partially observable environments
- policy iteration
- action space
- function approximators
- agent learns
- state and action spaces
- policy evaluation
- partially observable domains
- state action
- reward function
- particle filtering
- appearance model
- motion model
- evolutionary algorithm
- learning process
- machine learning