Safe reinforcement learning in uncertain contexts.
Dominik BaumannThomas B. SchönPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- machine learning
- reinforcement learning algorithms
- decision making
- control problems
- model free
- learning algorithm
- robotic control
- temporal difference
- policy search
- learning process
- temporal difference learning
- uncertain information
- learning classifier systems
- function approximators
- direct policy search
- markov decision process
- neural network
- markov decision processes
- artificial neural networks
- objective function
- data mining