Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics.
Tianqi ZhengPengcheng YouEnrique MalladaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- dynamical systems
- flow patterns
- reinforcement learning algorithms
- machine learning
- robotic control
- function approximation
- dynamic model
- state space
- optimal policy
- learning algorithm
- multi agent reinforcement learning
- model free
- critical points
- dynamic programming
- learning process
- information flow
- learning classifier systems
- markov decision processes
- temporal difference
- computer vision
- reinforcement learning methods
- mobile robot
- transfer learning
- real time