The AGV Battery Swapping Policy Based on Reinforcement Learning.
Min Seok LeeYoung Jae JangPublished in: CASE (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- reinforcement learning problems
- reward function
- partially observable environments
- policy iteration
- action selection
- control policy
- markov decision processes
- state and action spaces
- action space
- partially observable
- function approximators
- function approximation
- approximate dynamic programming
- policy gradient
- state space
- markov decision problems
- reinforcement learning algorithms
- state action
- control policies
- policy evaluation
- partially observable markov decision processes
- dynamic programming
- actor critic
- average reward
- flexible manufacturing systems
- control problems
- temporal difference
- model free
- decision problems
- inverse reinforcement learning
- agent learns
- machine learning
- long run
- transfer learning
- supervised learning
- mobile robot
- learning process
- finite state
- continuous state spaces
- data swapping
- reinforcement learning methods
- partially observable domains
- neural network
- learning algorithm
- multi agent
- information loss
- continuous state
- real robot
- temporal difference learning