Semantic Perception Swarm Policy with Deep Reinforcement Learning.
Tianle ZhangZhen LiuZhiqiang PuJianqiang YiPublished in: ICONIP (3) (2021)
Keyphrases
- reinforcement learning
- optimal policy
- selective perception
- policy search
- action selection
- markov decision process
- partially observable
- partially observable environments
- policy evaluation
- state space
- control policy
- reinforcement learning algorithms
- active exploration
- approximate dynamic programming
- swarm intelligence
- semantic information
- particle swarm optimization
- semantic similarity
- function approximation
- learning algorithm
- model free
- state and action spaces
- state action
- policy iteration
- natural language
- reinforcement learning problems
- actor critic
- dynamic programming
- control policies
- domain specific
- function approximators
- semantic knowledge
- reward function
- semantic web
- cooperative
- policy gradient
- evolutionary algorithm
- partially observable domains
- continuous state spaces
- markov decision processes
- machine learning
- inverse reinforcement learning
- transition model
- continuous state
- neural network
- infinite horizon
- semantic network
- domain ontology