Using Artificial Neural Networks in Reinforcement Learning Algorithms.
Martin GlovaGabriela AndrejkováPublished in: ITAT (2020)
Keyphrases
- using artificial neural networks
- reinforcement learning algorithms
- reinforcement learning
- markov decision processes
- state space
- model free
- artificial neural networks
- temporal difference
- eligibility traces
- reinforcement learning problems
- learning algorithm
- reinforcement learning methods
- partially observable environments
- function approximation
- neural network model
- policy search
- reward shaping
- dynamic environments
- monte carlo
- dynamic programming
- machine learning
- neural network
- reward function
- function approximators
- multiagent reinforcement learning