Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning.
Anoopkumar SonarVincent PacelliAnirudha MajumdarPublished in: L4DC (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- global optimization
- function approximation
- partially observable environments
- policy gradient
- optimization process
- markov decision processes
- optimization problems
- markov decision process
- decision problems
- reinforcement learning problems
- actor critic
- state space
- markov decision problems
- control problems
- reinforcement learning algorithms
- model free
- transfer learning
- optimization method
- least squares
- constrained optimization
- action space
- optimization algorithm
- optimization methods
- policy evaluation
- transition model
- search space
- learning algorithm