Assembly first working state

src/acting/acting.py

@@ -1,10 +1,10 @@
 import random
+from planning import planning
 
-
-def acting(env, h, g_r, g_s, f_v, f_p):
+def acting(env, h, g, f, n_simulation=10):
     """
     Inputs
-        h, g_r, g_s, f_v, f_p the five networks
+        h, g, f the five networks
         env game environment, class with the following methods:
             initial_state() -> state where
             state: Tensor of size 
@@ -24,11 +24,10 @@ def acting(env, h, g_r, g_s, f_v, f_p):
 
     o_prev = env.initial_state() # previous observation
 
-    mask = env.mask()
     is_terminal = False
 
     while not is_terminal:
-        nu_t, pi_t = planning(h, g_r, g_s, f_v, f_p, o_prev, mask) # running MCTS algorithm from the current state o_t
+        nu_t, pi_t = planning(h, g, f, o_prev, n_simulation) # running MCTS algorithm from the current state o_t 
         a = random.choices(range(len(pi_t)), weights = pi_t, k=1)[0] # Choosing the action randomly according to policy pi_t distribution
         r,o_new,is_terminal = env.step(a)
         search_statistics.append((o_prev,pi_t,a,r,nu_t))