Continual Reinforcement Learning in 3D Non-stationary Environments.
Vincenzo LomonacoKaran DesaiEugenio CulurcielloDavide MaltoniPublished in: CVPR Workshops (2020)
Keyphrases
- reinforcement learning
- function approximation
- model free
- reinforcement learning algorithms
- state space
- learning process
- direct policy search
- markov decision processes
- optimal policy
- learning algorithm
- dynamic programming
- temporal difference learning
- partially observable
- learning agents
- control problems
- relational reinforcement learning
- learning capabilities
- learning problems
- temporal difference
- optimal control
- database
- monte carlo
- supervised learning
- learning environment
- multi agent
- real time