Lifelong Reinforcement Learning with Modulating Masks.
Eseoghene Ben-IwhiwhuSaptarshi NathPraveen K. PillySoheil KolouriAndrea SoltoggioPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- edge detection
- markov decision processes
- st century
- reinforcement learning algorithms
- morphological operations
- decision making
- direct policy search
- robotic control
- markov decision process
- learning capabilities
- lifelong learning
- technology enhanced learning
- transfer learning
- learning activities
- action selection
- model free
- partially observable
- multi agent
- temporal difference learning
- stochastic approximation
- multi agent reinforcement learning
- policy search
- multiscale
- data mining