Reinforcement Learning Considering Worst Case and Equality within Episodes.
Toshihiro MatsuiPublished in: ICAART (1) (2020)
Keyphrases
- worst case
- reinforcement learning
- average case
- lower bound
- function approximation
- error bounds
- state space
- upper bound
- greedy algorithm
- learning algorithm
- model free
- markov decision processes
- worst case analysis
- running times
- reinforcement learning algorithms
- optimal control
- temporal difference
- robotic control
- markov decision process
- multi agent
- approximation algorithms
- np hard
- transfer learning
- multi agent systems
- optimal policy
- data sets
- event sequences
- dynamic programming
- learning problems
- autonomous learning
- multi agent reinforcement learning
- policy search