Bounds for off-policy prediction in reinforcement learning.
Ajin George JosephShalabh BhatnagarPublished in: IJCNN (2017)
Keyphrases
- reinforcement learning
- prediction accuracy
- function approximation
- upper bound
- prediction error
- prediction model
- lower bound
- prediction algorithm
- lower and upper bounds
- artificial neural networks
- genetic algorithm
- error bounds
- worst case
- markov decision processes
- transfer learning
- state space
- learning process
- multi agent
- social networks