Monte Carlo AssertionError: defaultdict(<function mc_control_importance_sampling.<locals>.<lambda> at 0x7f31699ffe18>, {}) (<class 'collections.defaultdict'>)

[NC25]

I have been working on a DQN using stable baselines and a discrete environment with 3 actions.

I am using the RL tutorial https://github.com/dennybritz/reinforcement-learning/blob/master/MC/MC%20Control%20with%20Epsilon-Greedy%20Policies%20Solution.ipynb

for reference

env = gym.make('fishing-v0')
model = DQN(MlpPolicy, env , verbose=2)
trained_model = model.learn(total_timesteps=10000)
  

But i am having some issues with my helper functions for the Monte Carlo methods

def mc_control_importance_sampling(env, num_episodes, discount = .99):
    """
    Monte Carlo Control Off-Policy Control using Weights for Sampling.
    Finds an optimal greedy policy.

    """
    
    # creates Q dictionary that maps obs to action values
    Q = defaultdict(lambda: np.zeros(env.action_space))
    #dictionary for weights
    C = defaultdict(lambda: np.zeros(env.action_space))
    
    # learn greedy policy
    target_policy = env.step(Q)
        
    for i_episode in range(1, num_episodes + 1):
        if i_episode % 1 == 0:
            print("\rEpisode {}/{}.".format(i_episode, num_episodes), end="")

        # Generate an episode to be tuple (state, action, reward) tuples
        episode = []
        obs = env.reset()
        for t in range(100):
            # Sample an action from our policy
            action, _states = trained_model.predict(obs)
            next_state, reward, done, _ = env.step(action)
            episode.append((state, action, reward))
            if done:
                break
            obs = next_obs
        
        # Sum of discounted returns
        G = 0.0
        # weights for return
        W = 1.0
        for t in range(len(episode))[::-1]:
            obs, action, reward = episode[t]
            G = discount * G + reward
            #  Add weights
            C[obs][action] += W
            # Update policy
            Q[obs][action] += (W / C[obs][action]) * (G - Q[obs][action]
                                                      
            if action !=  np.argmax(target_policy(obs)):
                break
            W = W * 1./behavior_policy(obs)[action]
        
    return Q, target_policy

When I call the function,

Q, policy = mc_control_importance_sampling(env, num_episodes=500000)

I get the error

AssertionError                            Traceback (most recent call last)
<ipython-input-58-eb968b9ff6e3> in <module>()
----> 1 Q, policy = mc_control_importance_sampling(env, num_episodes=500000)

1 frames
/content/gym_fishing/gym_fishing/envs/fishing_env.py in step(self, action)
     76     def step(self, action):
     77 
---> 78         assert self.action_space.contains(action), "%r (%s) invalid"%(action, type(action))
     79 
     80         if self.n_actions > 3:

AssertionError: defaultdict(<function mc_control_importance_sampling.<locals>.<lambda> at 0x7f31699ffe18>, {}) (<class 'collections.defaultdict'>) invalid
How do I fix this, your help would be appreciated.

I am not sure how to fix this,

thanks