An Idiosyncrasy of Time-discretization in Reinforcement Learning.
Kris De AsisRichard S. SuttonPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- state space
- temporal difference
- reinforcement learning algorithms
- model free
- dynamic programming
- optimal policy
- control problems
- markov decision processes
- discretization method
- robotic control
- preprocessing
- multi agent
- temporal difference learning
- iterative refinement
- learning agents
- data preprocessing
- optimal control
- partially observable
- learning capabilities
- data sets
- training data
- information retrieval
- machine learning