A Genetic Fuzzy System for Interpretable and Parsimonious Reinforcement Learning Policies.
Jordan T. BishopMarcus GallagherWill N. BrownePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- function approximation
- state space
- markov decision processes
- cooperative multi agent systems
- fitted q iteration
- partially observable markov decision processes
- reward function
- decision problems
- control policy
- reinforcement learning agents
- policy gradient methods
- hierarchical reinforcement learning
- reinforcement learning algorithms
- markov decision problems
- dynamic programming
- total reward
- macro actions
- robotic control
- multi agent reinforcement learning
- model free
- approximate policy iteration
- multiagent reinforcement learning
- probabilistic model
- learning process
- policy iteration
- tabula rasa
- transition model
- autonomous learning
- temporal difference learning
- learning agents
- average reward
- neural network
- temporal difference
- learning classifier systems
- learning problems
- transfer learning
- multi agent systems
- multi agent
- decision trees