Structured reward functions using STL: poster abstract.
Anand BalakrishnanJyotirmoy V. DeshmukhPublished in: HSCC (2019)
Keyphrases
- reward function
- markov decision processes
- inverse reinforcement learning
- reinforcement learning
- state space
- optimal policy
- multiple agents
- state variables
- transition probabilities
- structured data
- markov decision process
- policy search
- objective function
- data mining
- multi agent
- reinforcement learning algorithms
- transition model
- initially unknown