RangL: A Reinforcement Learning Competition Platform.
Viktor ZobernigRichard A. SaldanhaJinke HeErica van der SarJasper van DoornJia-Chen HuaLachlan Robert MasonAleksander CzechowskiDrago IndjicTomasz KosmalaAlessandro ZoccaSandjai BhulaiJorge Montalvo ArvizuClaude KlöcklJohn MoriartyPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- real time
- reinforcement learning algorithms
- temporal difference learning
- function approximation
- markov decision processes
- neural network
- dynamic programming
- model free
- learning process
- platform independent
- information retrieval
- state space
- software agents
- wireless sensor networks
- temporal difference
- learning capabilities
- markov decision process