Policy Gradients for Probabilistic Constrained Reinforcement Learning.
Weiqin ChenDharmashankar SubramanianSantiago PaternainPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- reinforcement learning algorithms
- action selection
- markov decision process
- state space
- reinforcement learning problems
- function approximators
- control policy
- partially observable environments
- policy evaluation
- markov decision problems
- function approximation
- actor critic
- reward function
- decision problems
- state action
- generative model
- state and action spaces
- policy gradient
- bayesian networks
- action space
- probabilistic logic
- probabilistic model
- dynamic programming
- partially observable markov decision processes
- partially observable
- reinforcement learning methods
- belief networks
- uncertain data
- least squares
- learning algorithm
- policy iteration
- long run
- supply chain