nip.scenario_base.environment#
Base class for the RL environment.
Classes
|
The base class for all Prover-Verifier RL environments. |
A message in the prompt for a language model API. |
|
|
Base for environments which handle non-tokenised text with nested array dicts. |
|
The base class for all Prover-Verifier RL environments which use tensordicts. |