8e5522ff50124a9ba05a7cdddfff7df8ebbafc14,examples/q_learning_grid.py,,,#,10

Before Change

from PyPi import policy as pi

// Logger
logger = logging.getLogger("logger")
logger.setLevel(logging.INFO)

// MDP
mdp = envs.GridWorld(3, 3, (2, 2))

After Change

// Regressor
discrete_actions = mdp.action_space.values
apprx_params = dict(shape=(8, 8))
approximator = apprxs.Regressor(approximator_class=apprxs.Tabular,
                                **apprx_params)
if args.action_regression:

Instances