Reward-machine-guided, self-paced reinforcement learning.
Cevahir KöprülüUfuk TopcuPublished in: UAI (2023)
Keyphrases
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- machine learning
- reward function
- markov decision processes
- partially observable environments
- reinforcement learning methods
- multi agent
- model free
- learning problems
- eligibility traces
- flowshop
- inverse reinforcement learning
- optimal control
- brain computer interface
- policy evaluation
- temporal difference
- total reward
- learning classifier systems
- average reward
- markov decision process
- action selection
- transfer learning
- supervised learning
- learning process
- genetic algorithm