Reinforcement Learning using Guided Observability.
Stephan WeigandPascal KlinkJan PetersJoni PajarinenPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- partially observable
- partial observability
- function approximation
- markov decision processes
- state space
- reinforcement learning methods
- reinforcement learning algorithms
- control problems
- temporal difference
- model free
- robotic control
- transfer learning
- optimal policy
- multi agent
- policy search
- machine learning
- planning problems
- learning problems
- learning capabilities
- least squares
- dynamic programming
- action space
- function approximators
- artificial intelligence
- multi agent reinforcement learning