Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning.
Kristopher De AsisAlan ChanSilviu PitisRichard S. SuttonDaniel GravesPublished in: AAAI (2020)
Keyphrases
- temporal difference methods
- reinforcement learning
- function approximation
- temporal difference
- function approximators
- policy search
- policy evaluation
- evolutionary methods
- reinforcement learning problems
- reinforcement learning algorithms
- model free
- td learning
- evaluation function
- action selection
- supervised learning
- neural network
- markov decision processes
- monte carlo
- least squares
- machine learning
- decision making
- control problems
- reward function
- differential evolution
- evolutionary computation
- semi supervised
- multi agent