declanoller / RWG_benchmarking

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

Add option of using static random seed #3

Closed declanoller closed 5 years ago

declanoller commented 5 years ago

There's randomness in the initial conditions of many env's that affects the outcomes. To be more systematic, it makes sense sometimes to specify a random seed value so runs at different times can be compared.

Hopefully this would be overcome by gathering enough statistics (trials), but it should be done anyway.