Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach.
Siddhant BhambriAmrita BhattacharjeeDimitri P. BertsekasPublished in: CoRR (2022)
Keyphrases
- adaptive control
- reinforcement learning methods
- reinforcement learning
- reinforcement learning algorithms
- control problems
- dynamical systems
- partially observable markov decision processes
- nonlinear systems
- partially observable
- feedback control
- control law
- optimal policy
- state space
- function approximation
- model free
- machine learning
- action space
- learning algorithm
- reward function
- markov decision processes
- control method
- dynamic programming
- temporal difference
- multi agent
- action selection
- finite state
- real valued
- control system