Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning.
Shengyi HuangQuentin GallouédecFlorian FeltenAntonin RaffinRousslan Fernand Julien DossaYanxiao ZhaoRyan SullivanViktor MakoviychukDenys MakoviichukMohamad H. DaneshCyril RoumégousJiayi WengChufan ChenMd Masudur RahmanJoão G. M. AraújoGuorui QuanDaniel TanTimo KleinRujikorn CharakornMark TowersYann BerthelotKinal MehtaDipam ChakrabortyArjun KGValentin CharrautChang YeZichen LiuLucas N. AlegreAlexander NikulinXiao HuTianlin LiuJongwook ChoiBrent YiPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- optimal policy
- markov decision processes
- rl algorithms
- temporal difference
- real world
- learning algorithm
- image sequences
- direct policy search
- multi agent
- real time
- partially observable
- actor critic
- control problems
- partially observable domains
- policy search
- supervised learning
- dynamic programming
- markov decision process
- continuous state
- policy iteration
- reinforcement learning agents
- reinforcement learning methods
- learning agents
- control policy
- optimal control
- complex domains
- action selection
- control strategies
- transfer learning
- learning classifier systems