Learning Reward Machines: A Study in Partially Observable Reinforcement Learning.
Rodrigo Toro IcarteEthan WaldieToryn Q. KlassenRichard Anthony ValenzanoMargarita P. CastroSheila A. McIlraithPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- partially observable
- partially observable environments
- state space
- learning process
- partially observable domains
- reward function
- partial observability
- action models
- markov decision processes
- hidden state
- inverse reinforcement learning
- reinforcement learning algorithms
- function approximation
- learning algorithm
- decision problems
- partial observations
- initially unknown
- model free
- dynamical systems
- learning capabilities
- partially observable markov decision processes
- graphical models
- learning tasks
- optimal solution
- multi agent
- knowledge base
- markov decision problems
- state action
- learning agent
- domain independent
- state variables