jaxdem.rl

Experimental reinforcement-learning models, environments, and trainers.

RL has a separate regression matrix and a narrower compatibility promise than the DEM core. See the RL support contract in the user guide.

Modules

action_spaces	Interface for bijectors that constrain the policy probability distribution.
env_wrappers	Wrappers that modify RL environments.
environments	Reinforcement-learning environment interface.
models	Interface for defining reinforcement learning models.
trainers	Interface for defining reinforcement learning model trainers.