Developing cooperative policies for multi-stage reinforcement learning tasks.
Jordan ErskineChris LehnertPublished in: CoRR (2022)
Keyphrases
- multistage
- learning tasks
- cooperative
- optimal policy
- reinforcement learning
- learning algorithm
- transfer learning
- multi task
- learning problems
- supervised learning
- machine learning
- single stage
- learning experience
- machine learning algorithms
- dynamic programming
- multi task learning
- function approximation
- production system
- lot sizing
- multi label
- kernel methods
- average cost
- multitask learning
- markov decision processes
- markov decision process
- state space
- long run
- infinite horizon
- semi supervised learning
- data mining