Towards Safe Continuing Task Reinforcement Learning.
Miguel Calvo-FullanaLuiz F. O. ChamonSantiago PaternainPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- state space
- learning algorithm
- optimal policy
- function approximation
- robotic control
- learning process
- reinforcement learning algorithms
- learning capabilities
- direct policy search
- policy search
- evolutionary learning
- stochastic approximation
- robot control
- control problems
- decision making
- machine learning
- learning problems
- multi agent
- model free
- markov decision processes
- learning agents
- temporal difference learning
- transfer learning
- artificial intelligence
- multi agent reinforcement learning
- transition model
- information systems
- expert systems