Skip to main content
costa-huang
Projects
cleanRL
Reports
policy lag

policy lag

Costa
Created on April 14|Last edited on April 15

10M20M30M40Mglobal_step10000200003000040000
10M20M30M40Mglobal_step0100200300400
510152025Time (minutes)0100200300400
510152025Time (minutes)81012141618
Longer policy lag
1
Shorter policy lag
1
learner sending shards
1
learner sending shards (periodic update
1


Created with ❤️ on Weights & Biases.

https://wandb.ai/costa-huang/cleanRL/reports/policy-lag--Vmlldzo0MDY5NjAy
Made with Weights & Biases. Sign up or log in to create reports like this one.