Goodhart's Law in Reinforcement Learning.
Jacek KarwowskiOliver HaymanXingjian BaiKlaus KiendlhoferCharlie GriffinJoar SkalsePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- reinforcement learning algorithms
- temporal difference
- machine learning
- multi agent reinforcement learning
- robotic control
- optimal control
- markov decision processes
- legal reasoning
- control problems
- supreme court
- relational reinforcement learning
- case law
- data sets
- action selection
- transfer learning
- learning process
- multi agent
- learning algorithm
- databases
- learning capabilities
- optimal policy
- evolutionary algorithm
- reinforcement learning methods
- real world