DecisionTransformerInterpretability
DecisionTransformerInterpretability copied to clipboard
Make it possible to track the preferences of the PPO in the app.
https://docs.google.com/document/d/1N1lVOXS5bLKYiXfoEeQoxxtI_0EfROi-JXcs-eYTCSA/edit?usp=sharing
I think this could be very valuable form the perspective of measuring the agent-simulators proclivity for modelling different agents in it's training distribution.