Off-policy and on-policy reinforcement learning with the Tsetlin machine.
Saeed Rahimi GorjiOle-Christoffer GranmoPublished in: Appl. Intell. (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- state space
- function approximation
- function approximators
- reinforcement learning problems
- markov decision processes
- reward function
- partially observable environments
- reinforcement learning algorithms
- actor critic
- partially observable
- policy gradient
- action space
- dynamic programming
- policy iteration
- infinite horizon
- state action
- temporal difference
- model free
- approximate dynamic programming
- state and action spaces
- control policy
- model free reinforcement learning
- control policies
- continuous state spaces
- policy evaluation
- inverse reinforcement learning
- average reward
- robotic control
- finite state
- approximate policy iteration
- machine learning
- exploration exploitation tradeoff
- continuous state
- rl algorithms
- reinforcement learning methods
- partially observable markov decision processes
- control problems
- long run
- decision problems
- multi agent
- decision making