State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards.
Miguel Calvo-FullanaSantiago PaternainLuiz F. O. ChamonAlejandro RibeiroPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- state space
- markov decision processes
- learning problems
- learning systems
- supervised learning
- machine learning
- function approximation
- inductive inference
- active learning
- prior knowledge
- knowledge acquisition
- temporal difference
- function approximators
- autonomous learning
- multiagent learning
- reward shaping
- multi armed bandits