P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL.
Sumanta DeyPallab DasguptaSoumyajit DeyPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- optimal policy
- global optimization
- optimization algorithm
- business process
- action selection
- optimization process
- optimization problems
- machine learning
- optimization method
- social capital
- markov decision process
- control policy
- learning algorithm
- policy gradient
- policy search
- model free reinforcement learning
- partially observable domains
- reinforcement learning algorithms
- infinite horizon
- function approximation
- decision problems
- business processes