Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning.
Sean VaskovWilko SchwartingChris L. BakerPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- direct policy search
- state space
- markov decision processes
- model free
- temporal difference learning
- control problems
- reinforcement learning algorithms
- temporal difference
- multi agent reinforcement learning
- robotic control
- transfer learning
- learning process
- multi agent
- robot control
- action space
- machine learning
- continuous state
- reinforcement learning methods
- logical framework
- action selection
- knowledge base
- learning problems
- expert systems