A note on the function approximation error bound for risk-sensitive reinforcement learning.
Prasenjit KarmakarShalabh BhatnagarPublished in: CoRR (2016)
Keyphrases
- function approximation
- error bounds
- risk sensitive
- model free
- reinforcement learning
- optimal control
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- control policies
- markov decision problems
- theoretical analysis
- function approximators
- utility function
- policy iteration
- worst case
- learning tasks
- learning algorithm
- state space
- transfer learning
- multi agent
- radial basis function
- neural network
- optimal policy
- partially observable
- machine learning
- sufficient conditions