A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints.
Bram De CoomanJohan A. K. SuykensPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- state space
- markov decision process
- function approximation
- viewpoint
- function approximators
- action space
- policy evaluation
- markov decision problems
- control policy
- policy iteration
- reinforcement learning algorithms
- model free
- constrained optimization
- approximate dynamic programming
- constraint satisfaction
- dynamic programming
- continuous state spaces
- actor critic
- machine learning
- reinforcement learning problems
- constraint programming
- markov decision processes
- learning process
- multi agent
- learning algorithm