Guiding Offline Reinforcement Learning Using a Safety Expert.
Richa VermaDurgesh KalwarHarshad KhadilkarBalaraman RavindranPublished in: COMAD/CODS (2024)
Keyphrases
- optimal control
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- knowledge base
- state space
- real time
- reinforcement learning methods
- model free
- learning process
- human experts
- optimal policy
- inverse reinforcement learning
- markov decision processes
- supervised learning
- multi agent
- decision making
- traffic accidents
- genetic algorithm
- expert advice
- data mining