examples moved

Author: ivanbelenky

src/examples/blackjack.py renamed to examples/blackjack.py

@@ -71,14 +71,6 @@ class ModelFree:
     transition. 
     '''
 
-    SOLVERS = {
-        'first_visit_mc': first_visit_monte_carlo,
-        'every_visit_mc': every_visit_monte_carlo, 
-        'off_policy_first_visit': off_policy_first_visit,
-        'off_policy_every_visit': off_policy_every_visit,
-        'temporal_difference': tdn,
-    }
-    
     def __init__(
         self,
         states: Sequence[Any],

src/examples/gridworld.py renamed to examples/gridworld.py

@@ -546,6 +546,4 @@ def _tdn(MF, n, alpha, n_episodes, max_steps, optimize, sample_step):
     return v, q, samples
 
 
-# temporal difference control SARSA, QLeearning, and some others
-
-
+# temporal difference control SARSA, QLeearning, and some others

src/model_free.py

@@ -1,10 +1,8 @@
 from abc import ABC, abstractmethod
 from typing import (
     Any, 
-    Union, 
     Sequence, 
     List, 
-    Dict,
     Tuple,
     Callable,
     NewType
@@ -18,7 +16,6 @@
 TOL = 1E-6
 MEAN_ITERS = int(1E4)
 
-
 class Policy(ABC):
     def __init__(self):
         pass
@@ -80,6 +77,7 @@ class Vpi(_TabularValues):
 class Qpi(_TabularValues):
     pass
 
+    
 
 VQPi = NewType('VQPi', Tuple[Vpi, Qpi, Policy])
 Samples = NewType('Samples', Tuple[int, List[Vpi], List[Qpi], List[np.ndarray]])