Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies.
Michael BeukmanDevon JarvisRichard KleinSteven JamesBenjamin RosmanPublished in: CoRR (2023)
Keyphrases
- context aware
- reinforcement learning
- contextual information
- optimal policy
- context awareness
- ubiquitous computing
- mobile devices
- context aware systems
- ambient intelligence
- policy search
- mobile users
- ubiquitous learning
- context aware services
- mobile applications
- location aware
- mobile computing
- reward function
- smart home
- smart environments
- current context
- state space
- pervasive computing
- markov decision processes
- ubiquitous environment
- learning algorithm
- distributed intelligent
- user context
- action recognition
- multi agent
- high level