Reinforcement Learning via Auxiliary Task Distillation.
Abhinav Narayan HarishLarry HeckJosiah P. HannaZsolt KiraAndrew SzotPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- learning algorithm
- multi agent
- model free
- state space
- machine learning
- reinforcement learning algorithms
- optimal policy
- robotic control
- policy search
- multi agent reinforcement learning
- temporal difference
- optimal control
- supervised learning
- decision making
- data mining
- real time
- learning process
- action selection
- multi agent systems
- partially observable
- transition model
- database