Info: numba.jit seems to be available.
For depth = 2 ...

Starting to explore every transitions up-to depth 2 for this root state:
    State : M = 2, K = 3 and t = 0, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

    Using these policies:
  - Player #0/2 uses Selfish_UCB_Ubar (which is <function Selfish_UCB_Ubar at 0x7f1769880950>)...
  - Player #1/2 uses Selfish_UCB_Ubar (which is <function Selfish_UCB_Ubar at 0x7f1769880950>)...
    Using these arms:
  - Arm #0/3 has mean mu_1 ...
  - Arm #1/3 has mean mu_2 ...
  - Arm #2/3 has mean mu_3 ...

For depth = 2, exploring from this node :
    State : M = 2, K = 3 and t = 0, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 27 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 10 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  1.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 10 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  1.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 13 different states...

For depth = 1, exploring from this node :
    State : M = 2, K = 3 and t = 1, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

  we saw 10 different states...



There are 144 unique leafs for depth 2...

 Leaf with probability = mu_1*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_2**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = (mu_1**2*mu_2**2 - 2*mu_1**2*mu_2 + mu_1**2 - 2*mu_1*mu_2**2 + 4*mu_1*mu_2 - 2*mu_1 + mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = (mu_2**2*mu_3**2 - 2*mu_2**2*mu_3 + mu_2**2 - 2*mu_2*mu_3**2 + 4*mu_2*mu_3 - 2*mu_2 + mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_2**2*mu_3**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_3**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_2*(mu_2 - 1)*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_2**2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = -mu_1*(mu_2 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_1*mu_2**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_2*mu_3**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_2**2*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_2**2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = (mu_2 - 1)*(mu_3 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_3**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_1**2*mu_2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_2*(mu_3 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1**2*mu_2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2*mu_3**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_1**2*mu_2*mu_3/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_2*(mu_2 - 1)*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_2**2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = (mu_2 - 1)*(mu_3 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_2**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1**2*mu_2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1**2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_1**2*mu_2*mu_3/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_3*(mu_2 - 1)**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_3*(mu_2 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_3*(mu_2 - 1)**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1*mu_3**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1**2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_3**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_1*(mu_3 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1**2*mu_3**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2**2*mu_3/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1**2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_3*(mu_2 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_3**2*(mu_2 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1**2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = mu_3**2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)**2*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = (mu_1**2*mu_3**2 - 2*mu_1**2*mu_3 + mu_1**2 - 2*mu_1*mu_3**2 + 4*mu_1*mu_3 - 2*mu_1 + mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_2**2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = (mu_1 - 1)*(mu_3 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = (mu_1 - 1)*(mu_3 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_2*mu_3**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = -mu_1**2*mu_2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2**2*mu_3/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = mu_1**2*(mu_2 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_2*mu_3**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = mu_3**2*(mu_1 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1*(mu_2 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1*mu_2**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = (mu_1 - 1)*(mu_2 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  1.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_3**2*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_2*(mu_3 - 1)*(mu_1**2 - 2*mu_1 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_1*(mu_3 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1**2*mu_2**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  1.  0.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = (mu_1 - 1)*(mu_2 - 1)*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1**2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_2**2*(mu_1 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_3*(mu_1 - 1)*(mu_2**2 - 2*mu_2 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_2*mu_3**2*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = -mu_1*mu_2*mu_3*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  1.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_1**2*(mu_3 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_2*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  0.  0.]] =: N


 Leaf with probability = -mu_2*mu_3**2*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  0.  1.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = -mu_1**2*mu_3*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 1.  0.  1.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_2**2*(mu_1 - 1)**2/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = -mu_2**2*mu_3*(mu_1 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  1.]
 [ 0.  1.  0.]] =: N


 Leaf with probability = mu_2*mu_3*(mu_1 - 1)*(mu_2 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  1.  1.]] =: N


 Leaf with probability = -mu_1*(mu_1 - 1)*(mu_2 - 1)*(mu_3 - 1)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  0.  0.]
 [ 1.  0.  0.]] =: N


 Leaf with probability = mu_1*mu_2*(mu_3**2 - 2*mu_3 + 2)/18:
    State : M = 2, K = 3 and t = 3, depth = 0.
 =: Stilde
[[ 0.  1.  0.]
 [ 1.  0.  0.]] =: N


Done for exploring every transitions up-to depth 2 for this root state:
    State : M = 2, K = 3 and t = 0, depth = 2.
 =: Stilde
[[ 0.  0.  0.]
 [ 0.  0.  0.]] =: N

    Using these policies:
  - Player #0/2 uses Selfish_UCB_Ubar (which is <function Selfish_UCB_Ubar at 0x7f1769880950>)...
  - Player #1/2 uses Selfish_UCB_Ubar (which is <function Selfish_UCB_Ubar at 0x7f1769880950>)...
    Using these arms:
  - Arm #0/3 has mean mu_1 ...
  - Arm #1/3 has mean mu_2 ...
  - Arm #2/3 has mean mu_3 ...

There were 144 unique leafs for depth 2...


For depth 2, 0 leafs were found to be absorbing, and the probability of reaching any absorbing leaf is 0...

==> Numerically, for uniformly spanned means = [0.10000000000000001, 0.5, 0.90000000000000002], this probability is = 0 ...
Creating a dot graph from the state...
Saving the dot graph to 'plots/trees/Tree_exploration_K=3_M=2_depth=2__Selfish_UCB_Ubar.gv.svg'...


[Enter] to continue...