Reinforcement learning beyond the Bellman equation: Exploring critic objectives using evolution.
Abe LeiteMadhavun CandadaiEduardo J. IzquierdoPublished in: ALIFE (2020)
Keyphrases
- reinforcement learning
- actor critic
- temporal difference
- function approximation
- reinforcement learning algorithms
- temporal difference learning
- policy gradient
- approximate dynamic programming
- state space
- markov decision processes
- neuro fuzzy
- optimal control
- learning process
- optimal policy
- gradient method
- model free
- temporal evolution
- control problems
- learning algorithm
- action selection
- linear program
- finite state
- step size
- average reward
- monte carlo
- mobile robot
- reinforcement learning methods
- search algorithm
- multi agent
- machine learning
- hamilton jacobi