Curriculum in Gradient-Based Meta-Reinforcement Learning.
Bhairav MehtaTristan DeleuSharath Chandra RaparthyChristopher J. PalLiam PaullPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- model free
- function approximation
- state space
- reinforcement learning algorithms
- multi agent
- high school
- machine learning
- temporal difference
- dynamic programming
- markov decision processes
- meta level
- multi agent reinforcement learning
- primary school
- optimal control
- science teachers
- policy search
- learning algorithm
- computer science curriculum
- science education
- professional development
- learning problems
- transfer learning
- learning process