NeoRL: Efficient Exploration for Nonepisodic RL.
Bhavya SukhijaLenart TrevenFlorian DörflerStelian CorosAndreas KrausePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- model free
- autonomous learning
- learning agents
- learning process
- temporal difference
- multi agent
- state space
- learning classifier systems
- markov decision processes
- markov decision process
- reinforcement learning algorithms
- real time
- transfer learning
- search algorithm
- neural network
- data sets