search

declanoller / RWG_benchmarking

Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing
MIT License
5 stars 0 forks source link

Add distributional stats #1

Closed declanoller closed 5 years ago

declanoller commented 5 years ago

It's not as informative to only have a single solve time/avg score, due to randomness. It would be better, for benchmarking, to run an ensemble of the agents, and form a distribution. Even 10 of them would let us get a sense of the spread.

declanoller commented 5 years ago

Solved with PR #5