Policy Gradient Method For Robust Reinforcement Learning.
Yue WangShaofeng ZouPublished in: ICML (2022)
Keyphrases
- gradient method
- actor critic
- policy gradient
- reinforcement learning
- optimal policy
- convergence rate
- negative matrix factorization
- convex formulation
- optimization methods
- markov decision process
- step size
- information retrieval
- action selection
- function approximation
- document clustering
- markov decision processes
- state space
- reinforcement learning algorithms
- partially observable markov decision processes
- multi objective
- control policy
- feature vectors
- state action
- keywords
- learning algorithm
- neural network
- natural gradient learning