Optimizing Representations and Policies for Question Sequencing using Reinforcement Learning.
Aqil Zainal AzharAvi SegalKobi GalPublished in: EDM (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- state space
- control policies
- reward function
- markov decision problems
- control policy
- partially observable markov decision processes
- function approximation
- markov decision processes
- policy gradient methods
- total reward
- reinforcement learning agents
- multi agent
- infinite horizon
- finite state
- reinforcement learning algorithms
- machine learning
- dynamic programming
- exploration exploitation tradeoff
- multi agent reinforcement learning
- transfer learning
- partially observable
- continuous state
- temporal difference learning
- multiagent reinforcement learning
- function approximators
- macro actions
- decision problems
- model free