Meta-Reinforcement Learning Using Model Parameters.
Gabriel HartmannAmos AzariaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- meta level
- state space
- model free
- optimal policy
- machine learning
- robotic control
- multi agent
- direct policy search
- data sets
- meta reasoning
- markov decision processes
- reinforcement learning methods
- learning algorithm
- policy search
- transition model
- multi agent reinforcement learning
- markov decision process
- robot control
- partially observable
- dynamic programming
- temporal difference
- action selection
- website
- case study
- transfer learning
- search space
- hidden markov models