Hi, I used ML-agent train agent with curiosity, so How can I record the agent’s intrinsic and extrinsic rewards for every observation and timestep?
or how do I record the rewards for every observation and timestep?
The cumulative reward per timestep for all reward signals is reported in tensorboard. Are you asking for a different statistic than this?
Yes, when I use curiosity configuration, how can I distinguish between intrinsic and extrinsic rewards? so In Ml-agent, the only statistic I can know is the cumulative reward per timestep for all reward signals?
If you open the Policy tab in tensorboard, you will see Curiosity Reward and Extrinsic Reward as separate plots.
got it, thanks.