Group Equivariant Deep Reinforcement Learning.
Arnab Kumar MondalPratheeksha NairKaleem SiddiqiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- case study
- multi agent
- learning process
- state space
- stochastic approximation
- learning algorithm
- multiscale
- group membership
- reinforcement learning methods
- deep learning
- reinforcement learning algorithms
- temporal difference
- group members
- model free
- optimal control
- machine learning
- optimal policy
- search algorithm