Limit Action Space to Enhance Drone Control with Deep Reinforcement Learning.
Sooyoung JangNoh-Sam ParkPublished in: ICTC (2020)
Keyphrases
- action space
- reinforcement learning
- control policies
- state space
- markov decision processes
- action selection
- control problems
- state and action spaces
- real valued
- continuous state
- optimal control
- continuous state spaces
- markov decision process
- state information
- reinforcement learning methods
- control strategies
- control system
- adaptive control
- state action
- function approximation
- stochastic processes
- control policy
- control strategy
- function approximators
- learning algorithm
- partially observable
- reinforcement learning algorithms
- optimal policy
- machine learning
- single agent
- temporal difference
- model free
- long run