!pip install aicrowd-cli > /dev/null

import os

AICROWD_DATASET_PATH = os.getenv("DATASET_PATH", os.getcwd()+"/13d77bb0-b325-4e95-a03b-833eb6694acd_a2_taxi_inputs.zip")
AICROWD_RESULTS_DIR = os.getenv("OUTPUTS_DIR", "results")

!unzip $AICROWD_DATASET_PATH

DATASET_DIR = 'inputs/'

import numpy as np

class TaxiEnv_HW2:
    def __init__(self, states, actions, probabilities, rewards, initial_policy):
        self.possible_states = states
        self._possible_actions = {st: ac for st, ac in zip(states, actions)}
        self._ride_probabilities = {st: pr for st, pr in zip(states, probabilities)}
        self._ride_rewards = {st: rw for st, rw in zip(states, rewards)}
        self.initial_policy = initial_policy
        self._verify()

    def _check_state(self, state):
        assert state in self.possible_states, "State %s is not a valid state" % state

    def _verify(self):
        """ 
        Verify that data conditions are met:
        Number of actions matches shape of next state and actions
        Every probability distribution adds up to 1 
        """
        ns = len(self.possible_states)
        for state in self.possible_states:
            ac = self._possible_actions[state]
            na = len(ac)

            rp = self._ride_probabilities[state]
            assert np.all(rp.shape == (na, ns)), "Probabilities shape mismatch"
        
            rr = self._ride_rewards[state]
            assert np.all(rr.shape == (na, ns)), "Rewards shape mismatch"

            assert np.allclose(rp.sum(axis=1), 1), "Probabilities don't add up to 1"

    def possible_actions(self, state):
        """ Return all possible actions from a given state """
        self._check_state(state)
        return self._possible_actions[state]

    def ride_probabilities(self, state, action):
        """ 
        Returns all possible ride probabilities from a state for a given action
        For every action a list with the returned with values in the same order as self.possible_states
        """
        actions = self.possible_actions(state)
        ac_idx = actions.index(action)
        return self._ride_probabilities[state][ac_idx]

    def ride_rewards(self, state, action):
        actions = self.possible_actions(state)
        ac_idx = actions.index(action)
        return self._ride_rewards[state][ac_idx]

def check_taxienv():
    # These are the values as used in the pdf, but they may be changed during submission, so do not hardcode anything

    states = ['A', 'B', 'C']

    actions = [['1','2','3'], ['1','2'], ['1','2','3']]

    probs = [np.array([[1/2,  1/4,  1/4],
                    [1/16, 3/4,  3/16],
                    [1/4,  1/8,  5/8]]),

            np.array([[1/2,   0,     1/2],
                    [1/16,  7/8,  1/16]]),

            np.array([[1/4,  1/4,  1/2],
                    [1/8,  3/4,  1/8],
                    [3/4,  1/16, 3/16]]),]

    rewards = [np.array([[10,  4,  8],
                        [ 8,  2,  4],
                        [ 4,  6,  4]]),

            np.array([[14,  0, 18],
                        [ 8, 16,  8]]),

            np.array([[10,  2,  8],
                        [6,   4,  2],
                        [4,   0,  8]]),]
    initial_policy = {'A': '1', 'B': '1', 'C': '1'}

    env = TaxiEnv_HW2(states, actions, probs, rewards, initial_policy)
    print("All possible states", env.possible_states)
    print("All possible actions from state B", env.possible_actions('B'))
    print("Ride probabilities from state A with action 2", env.ride_probabilities('A', '2'))
    print("Ride rewards from state C with action 3", env.ride_rewards('C', '3'))

    base_kwargs = {"states": states, "actions": actions, 
                "probabilities": probs, "rewards": rewards,
                "initial_policy": initial_policy}
    return base_kwargs

base_kwargs = check_taxienv()
env = TaxiEnv_HW2(**base_kwargs)

# 1.1 Policy Iteration
def policy_iteration(taxienv, gamma):
    # A list of all the states
    states = taxienv.possible_states
    # Initial values
    values = {s: 0 for s in states}

    # This is a dictionary of states to policies -> e.g {'A': '1', 'B': '2', 'C': '1'}
    policy = taxienv.initial_policy.copy()

    ## Begin code here

    #initialization

    J_values = values

    #J_values = {s: 0 for s in states}
    #policy = {s: '1' for s in states}#1 = cruise

    tol = 1e-8
    delta = 0.0

    #external while loop to find optimal policy
    while True:
        #internal while loop, value function estimation for a fixed policy
        while True:
            delta = 0.0

            for current_state in states:
                #store value at current state before updating it
                j = J_values[current_state]

                #find action at current state from the policy map
                current_action          = policy[current_state]
                ride_probs              = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards            = taxienv.ride_rewards(current_state, current_action)
                #Bellman Expectation equation
                J_values[current_state] = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))

                #update delta
                delta                   = max(delta, abs(j - J_values[current_state]))

            #terminate while loop when delta falls below tol 
            if(delta < tol):
                break
    
        #calculate optimal policy
        done = 1
        for current_state in states:
            #b = PI(s), store the previous policy before it gets updated for current_state
            b = policy[current_state]

            #calculate values for all actions at current state and pick the argmax of them for optimal policy
            action_values_at_state = []
            possible_actions = taxienv.possible_actions(current_state)
            for current_action in possible_actions:
                ride_probs = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards = taxienv.ride_rewards(current_state, current_action)
                expected_value_for_action = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))
                action_values_at_state.append(expected_value_for_action)

            policy[current_state] = str(possible_actions[np.argmax(action_values_at_state)])

            #compare previous to current policy and if any change occurs we are not done yet and need to do more iterations
            if(b != policy[current_state]):
                done = 0
            
        if(done == 1):
            break

    #return J_values, policy

    values = J_values

    # Hints - 
    # Do not hardcode anything
    # Only the final result is required for the results
    # Put any extra data in "extra_info" dictonary for any plots etc
    # Use the helper functions taxienv.ride_rewards, taxienv.ride_probabilities,  taxienv.possible_actions
    # For terminating condition use the condition exactly mentioned in the pdf

    
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {}

    ## Do not edit below this line

    # Final results
    return {"Expected Reward": values, "Policy": policy}, extra_info

# 1.2 Policy Iteration with different values of gamma
def run_policy_iteration(env):
    gamma_values = np.arange(5, 100, 5)/100
    results, extra_info = {}, {}
    for gamma in gamma_values:
        results[gamma], extra_info[gamma] = policy_iteration(env, gamma)
    return results, extra_info

results, extra_info = run_policy_iteration(env)

# 1.3 Modified Policy Iteration
def modified_policy_iteration(taxienv, gamma, m):
    # A list of all the states
    states = taxienv.possible_states
    # Initial values
    values = {s: 0 for s in states}

    # This is a dictionary of states to policies -> e.g {'A': '1', 'B': '2', 'C': '1'}
    policy = taxienv.initial_policy.copy()

    ## Begin code here

    #initialization

    J_values = values

    #J_values = {s: 0 for s in states}
    #policy = {s: '1' for s in states} #1 = cruise

    delta = 0.0

    #external while loop to find optimal policy
    while True:
        #internal for loop, just loop m+1 times irrespective of convergence
        #value function estimation for a fixed policy
        for k in range(0, m + 1):
            for current_state in states:
                #find action at current state from the policy map
                current_action          = policy[current_state]
                ride_probs              = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards            = taxienv.ride_rewards(current_state, current_action)
                #Bellman Expectation equation
                J_values[current_state] = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))
    
        #calculate optimal policy
        done = 1
        for current_state in states:
            #b = PI(s), store the previous policy before it gets updated for current_state
            b = policy[current_state]

            #calculate values for all actions at current state and pick the argmax of them for optimal policy
            action_values_at_state = []
            possible_actions = taxienv.possible_actions(current_state)
            for current_action in possible_actions:
                ride_probs = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards = taxienv.ride_rewards(current_state, current_action)
                expected_value_for_action = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))
                action_values_at_state.append(expected_value_for_action)

            policy[current_state] = str(possible_actions[np.argmax(action_values_at_state)])

            #compare previous to current policy and if any change occurs we are not done yet and need to do more iterations
            if(b != policy[current_state]):
                done = 0
            
        if(done == 1):
            break

    #return J_values, policy
    values = J_values

    # Hints - 
    # Do not hardcode anything
    # Only the final result is required for the results
    # Put any extra data in "extra_info" dictonary for any plots etc
    # Use the helper functions taxienv.ride_rewards, taxienv.ride_probabilities,  taxienv.possible_actions
    # For terminating condition use the condition exactly mentioned in the pdf

    
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {}

    ## Do not edit below this line


    # Final results
    return {"Expected Reward": values, "Policy": policy}, extra_info

def run_modified_policy_iteration(env):
    m_values = np.arange(1, 15)
    gamma = 0.9
    results, extra_info = {}, {}
    for m in m_values:
        results[m], extra_info[m] = modified_policy_iteration(env, gamma, m)
    return results, extra_info

results, extra_info = run_modified_policy_iteration(env)

# 1.4 Value Iteration
def value_iteration(taxienv, gamma):
    # A list of all the states
    states = taxienv.possible_states
    # Initial values
    values = {s: 0 for s in states}

    # This is a dictionary of states to policies -> e.g {'A': '1', 'B': '2', 'C': '1'}
    policy = taxienv.initial_policy.copy()

    ## Begin code here
    
    J_values = values

    #J_values = {s: 0 for s in states}
    H_values = {s: 0 for s in states}
  

    gamma = 0.9
    tol = 1e-8
    delta = 0.0

    #repeat with while loop
    while True:
        delta = 0.0
        for current_state in states:
            #calculate values for all actions at current state and pick the maximum of them, update H
            action_values_at_state = []
            possible_actions = taxienv.possible_actions(current_state)
            for current_action in possible_actions:
                ride_probs = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards = taxienv.ride_rewards(current_state, current_action)
                expected_value_for_action = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))
                action_values_at_state.append(expected_value_for_action)

            H_values[current_state] = np.amax(action_values_at_state)
            policy[current_state] = str(possible_actions[np.argmax(action_values_at_state)])

            #update delta, after values have been changed
            delta = max(delta, abs(H_values[current_state] - J_values[current_state]))

        #update J from H
        for current_state in states:
            J_values[current_state] = H_values[current_state]

        #break while loop with until condition
        if(delta < tol):
            break
    
    #all_values.append(values.copy())
    #all_policies.append(policy.copy())

    values = J_values
    #policy = policy_opt
    #return J_values

    # Hints - 
    # Do not hardcode anything
    # Only the final result is required for the results
    # Put any extra data in "extra_info" dictonary for any plots etc
    # Use the helper functions taxienv.ride_rewards, taxienv.ride_probabilities,  taxienv.possible_actions
    # For terminating condition use the condition exactly mentioned in the pdf


    # Put your extra information needed for plots etc in this dictionary
    extra_info = {}

    ## Do not edit below this line

    # Final results
    return {"Expected Reward": values, "Policy": policy}, extra_info

def run_value_iteration(env):
    gamma_values = np.arange(5, 100, 5)/100
    results = {}
    results, extra_info = {}, {}
    for gamma in gamma_values:
        results[gamma], extra_info[gamma] = value_iteration(env, gamma)
    return results, extra_info
  
results, extra_info = run_value_iteration(env)

# 1.4 Gauss Seidel Value Iteration
def gauss_seidel_value_iteration(taxienv, gamma):
    # A list of all the states
    # For Gauss Seidel Value Iteration - iterate through the values in the same order
    states = taxienv.possible_states

    # Initial values
    values = {s: 0 for s in states}

    # This is a dictionary of states to policies -> e.g {'A': '1', 'B': '2', 'C': '1'}
    policy = taxienv.initial_policy.copy()

    # Hints - 
    # Do not hardcode anything
    # For Gauss Seidel Value Iteration - iterate through the values in the same order as taxienv.possible_states
    # Only the final result is required for the results
    # Put any extra data in "extra_info" dictonary for any plots etc
    # Use the helper functions taxienv.ride_rewards, taxienv.ride_probabilities,  taxienv.possible_actions
    # For terminating condition use the condition exactly mentioned in the pdf

    ## Begin code here

    J_values = values
    #J_values = {s: 0 for s in states}

    gamma = 0.9
    tol = 1e-8
    delta = 0.0

    while True:
        delta = 0.0
        for current_state in states:
            #j = J(s), store previous value before it gets updated for current_state
            j = J_values[current_state]

            #calculate values for all actions at current state and pick the maximum of them
            action_values_at_state = []
            possible_actions = taxienv.possible_actions(current_state)
            for current_action in possible_actions:
                ride_probs                  = taxienv.ride_probabilities(current_state, current_action)
                ride_rewards                = taxienv.ride_rewards(current_state, current_action)
                expected_value_for_action   = np.dot(ride_probs, list(np.add(ride_rewards, np.asarray(gamma) * list(J_values.values()))))
                action_values_at_state.append(expected_value_for_action)

            J_values[current_state] = np.amax(action_values_at_state)
            policy[current_state] = str(possible_actions[np.argmax(action_values_at_state)])

            #update delta, after values in J have been updated for current_state
            delta = max(delta, abs(j - J_values[current_state]))

        if(delta < tol):
            break
    
    #return J_values
    values = J_values
    
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {}

    ## Do not edit below this line

    # Final results
    return {"Expected Reward": values, "Policy": policy}, extra_info

def run_gauss_seidel_value_iteration(env):
    gamma_values = np.arange(5, 100, 5)/100
    results = {}
    results, extra_info = {}, {}
    for gamma in gamma_values:
        results[gamma], extra_info[gamma] = gauss_seidel_value_iteration(env, gamma)
    return results, extra_info

results, extra_info = run_gauss_seidel_value_iteration(env)

# Do not edit this cell
def get_results(kwargs):

    taxienv = TaxiEnv_HW2(**kwargs)

    policy_iteration_results = run_policy_iteration(taxienv)[0]
    modified_policy_iteration_results = run_modified_policy_iteration(taxienv)[0]
    value_iteration_results = run_value_iteration(taxienv)[0]
    gs_vi_results = run_gauss_seidel_value_iteration(taxienv)[0]

    final_results = {}
    final_results["policy_iteration"] = policy_iteration_results
    final_results["modifed_policy_iteration"] = modified_policy_iteration_results
    final_results["value_iteration"] = value_iteration_results
    final_results["gauss_seidel_iteration"] = gs_vi_results

    return final_results

# Do not edit this cell, generate results with it as is
if not os.path.exists(AICROWD_RESULTS_DIR):
    os.mkdir(AICROWD_RESULTS_DIR)

for params_file in os.listdir(DATASET_DIR):
  kwargs = np.load(os.path.join(DATASET_DIR, params_file), allow_pickle=True).item()
  results = get_results(kwargs)
  idx = params_file.split('_')[-1][:-4]
  np.save(os.path.join(AICROWD_RESULTS_DIR, 'results_' + idx), results)

# Check your score on the given test cases (There are more private test cases not provided)
target_folder = 'targets'
result_folder = AICROWD_RESULTS_DIR

def check_algo_match(results, targets):
    param_matches = []
    for k in results:
        param_results = results[k]
        param_targets = targets[k]
        policy_match = param_results['Policy'] == param_targets['Policy']
        rv = [v for k, v in param_results['Expected Reward'].items()]
        tv = [v for k, v in param_targets['Expected Reward'].items()]
        rewards_match = np.allclose(rv, tv, rtol=3)
        equal = rewards_match and policy_match
        param_matches.append(equal)
    return np.mean(param_matches)

def check_score(target_folder, result_folder):
    match = []
    for out_file in os.listdir(result_folder):
        res_file = os.path.join(result_folder, out_file)
        results = np.load(res_file, allow_pickle=True).item()
        idx = out_file.split('_')[-1][:-4]  # Extract the file number
        target_file = os.path.join(target_folder, f"targets_{idx}.npy")
        targets = np.load(target_file, allow_pickle=True).item()
        algo_match = []
        for k in targets:
            algo_results = results[k]
            algo_targets = targets[k]
            algo_match.append(check_algo_match(algo_results, algo_targets))
        match.append(np.mean(algo_match))
    return np.mean(match)

if os.path.exists(target_folder):
    print("Shared data Score (normalized to 1):", check_score(target_folder, result_folder))

## Visualize policy iteration with multiple values of gamma

!DATASET_PATH=$AICROWD_DATASET_PATH aicrowd notebook submit -c iit-m-rl-assignment-2-taxi -a assets