main.py

for _ in range(5000):
    observations += [observation.tolist()] # Record the observations for normalization and replay
    
    if done: # If the simulation was over last iteration, exit loop
      break
        
    # Pick an action according to the policy matrix
    outcome = np.dot(policy, observation)
    action = 1 if outcome > 0 else 0
    
    # Make the action, record reward
    observation, reward, done, info = env.step(action)
    score += reward

  return score, observations