Ökolopoly: Case Study on Large Action Spaces in Reinforcement Learning.
Raphael C. EngelhardtRalitsa RaychevaMoritz LangeLaurenz WiskottWolfgang KonenPublished in: LOD (2) (2023)
Keyphrases
- action space
- case study
- reinforcement learning
- state space
- state and action spaces
- markov decision processes
- continuous state
- real valued
- state action
- control policies
- action selection
- reinforcement learning methods
- continuous state spaces
- function approximators
- markov decision process
- model free
- single agent
- function approximation
- skill learning
- machine learning
- robot navigation
- stochastic processes
- reinforcement learning problems
- markov chain
- dynamic programming
- cooperative
- temporal difference
- reinforcement learning algorithms
- finite state
- learning algorithm
- control problems
- policy search
- supervised learning