SO(2)-Equivariant Reinforcement Learning.
Dian WangRobin WaltersRobert PlattPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- state space
- learning algorithm
- temporal difference
- dynamic programming
- robotic control
- control problems
- rotation invariant
- markov decision processes
- optimal policy
- multi agent
- real world
- hidden markov models
- action selection
- case study
- data sets
- learning agents
- reinforcement learning methods
- matrix valued
- policy search
- database