Lifelong Reinforcement Learning with Modulating Masks.
Eseoghene Ben-IwhiwhuSaptarshi NathPraveen K. PillySoheil KolouriAndrea SoltoggioPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- markov decision processes
- edge detection
- state space
- technology enhanced learning
- st century
- optimal policy
- machine learning
- learning process
- multi agent
- learning activities
- robotic control
- robot control
- partially observable
- lifelong learning
- markov decision process
- learning scenarios
- reinforcement learning methods
- stochastic approximation
- direct policy search
- temporal difference
- action selection
- model free
- morphological operations
- database
- supervised learning
- dynamic programming
- active learning
- real world
- neural network