Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing.
Declan OllerTobias GlasmachersGiuseppe CuccuPublished in: AAMAS (2020)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- temporal difference learning
- decision trees
- temporal difference
- state space
- machine learning
- reinforcement learning algorithms
- optimal control
- optimal policy
- dynamic programming
- transfer learning
- markov decision processes
- model free
- weighting scheme
- learning process
- database systems
- learning capabilities
- information systems
- autonomous learning
- data sets