Keyphrases
- reward function
- markov decision processes
- inverse reinforcement learning
- state space
- reinforcement learning
- reinforcement learning algorithms
- optimal policy
- partially observable
- multiple agents
- transition probabilities
- state variables
- initially unknown
- markov decision process
- hierarchical reinforcement learning
- machine learning
- minimax regret
- markov chain
- control policies
- generative model
- transition model
- higher order
- social networks