Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing.
Declan OllerTobias GlasmachersGiuseppe CuccuPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- reinforcement learning algorithms
- robotic control
- uniformly distributed
- weighting scheme
- model free
- optimal control
- temporal difference
- database
- state space
- dynamic programming
- multi agent
- learning environment
- case study
- decision trees
- learning capabilities
- learning agents
- weight function
- benchmark suite
- data sets