Hypernetworks in Meta-Reinforcement Learning.
Jacob BeckMatthew Thomas JacksonRisto VuorioShimon WhitesonPublished in: CoRL (2022)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- temporal difference
- machine learning
- state space
- optimal policy
- temporal difference learning
- control problems
- learning environment
- meta level
- markov decision processes
- neural network
- learning capabilities
- model free
- dynamic environments
- learning algorithm
- data sets
- transfer learning
- action selection
- evolutionary algorithm
- multi agent systems
- reinforcement learning methods
- policy search
- meta reasoning
- perceptual aliasing