Evolving Rewards to Automate Reinforcement Learning.
Aleksandra FaustAnthony G. FrancisDar MehtaPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- state space
- reinforcement learning algorithms
- model free
- temporal difference
- partially observable
- machine learning
- reward shaping
- transfer learning
- supervised learning
- learning process
- multi agent
- reward function
- learning algorithm
- genetic algorithm
- markov decision process
- control policy
- transition model
- learning problems
- action space
- multi agent reinforcement learning
- policy search
- neural network
- direct policy search