!pip install aicrowd-cli > /dev/null

import os

AICROWD_DATASET_PATH = os.getenv("DATASET_PATH", os.getcwd()+"/a5562c7d-55f0-4d06-841c-110655bb04ec_a2_gridworld_inputs.zip")
AICROWD_RESULTS_DIR = os.getenv("OUTPUTS_DIR", "results")

!unzip -q $AICROWD_DATASET_PATH

DATASET_DIR = 'inputs/'

import numpy as np

class GridEnv_HW2:
    def __init__(self, 
                 goal_location, 
                 action_stochasticity,
                 non_terminal_reward,
                 terminal_reward,
                 grey_in,
                 brown_in,
                 grey_out,
                 brown_out
                ):

        # Do not edit this section 
        self.action_stochasticity = action_stochasticity
        self.non_terminal_reward = non_terminal_reward
        self.terminal_reward = terminal_reward
        self.grid_size = [10, 10]

        # Index of the actions 
        self.actions = {'N': (1, 0), 
                        'E': (0,1),
                        'S': (-1,0), 
                        'W': (0,-1)}
        
        self.perpendicular_order = ['N', 'E', 'S', 'W']
        
        l = ['normal' for _ in range(self.grid_size[0]) ]
        self.grid = np.array([l for _ in range(self.grid_size[1]) ], dtype=object)

        self.grid[goal_location[0], goal_location[1]] = 'goal'
        self.goal_location = goal_location

        for gi in grey_in:
            self.grid[gi[0],gi[1]] = 'grey_in'
        for bi in brown_in:    
            self.grid[bi[0], bi[1]] = 'brown_in'

        for go in grey_out:    
            self.grid[go[0], go[1]] = 'grey_out'
        for bo in brown_out:    
            self.grid[bo[0], bo[1]] = 'brown_out'

        self.grey_outs = grey_out
        self.brown_outs = brown_out

    def _out_of_grid(self, state):
        if state[0] < 0 or state[1] < 0:
            return True
        elif state[0] > self.grid_size[0] - 1:
            return True
        elif state[1] > self.grid_size[1] - 1:
            return True
        else:
            return False

    def _grid_state(self, state):
        return self.grid[state[0], state[1]]        
        
    def get_transition_probabilites_and_reward(self, state, action):
        """ 
        Returns the probabiltity of all possible transitions for the given action in the form:
        A list of tuples of (next_state, probability, reward)
        Note that based on number of state and action there can be many different next states
        Unless the state is All the probabilities of next states should add up to 1
        """

        grid_state = self._grid_state(state)
        
        if grid_state == 'goal':
            return [(self.goal_location, 1.0, 0.0)]
        elif grid_state == 'grey_in':
            npr = []
            for go in self.grey_outs:
                npr.append((go, 1/len(self.grey_outs), 
                            self.non_terminal_reward))
            return npr
        elif grid_state == 'brown_in':
            npr = []
            for bo in self.brown_outs:
                npr.append((bo, 1/len(self.brown_outs), 
                            self.non_terminal_reward))
            return npr
        
        direction = self.actions.get(action, None)
        if direction is None:
            raise ValueError("Invalid action %s , please select among" % action, list(self.actions.keys()))

        dir_index = self.perpendicular_order.index(action)
        wrap_acts = self.perpendicular_order[dir_index:] + self.perpendicular_order[:dir_index]
        next_state_probs = {}
        for prob, a in zip(self.action_stochasticity, wrap_acts):
            d = self.actions[a]
            next_state = (state[0] + d[0]), (state[1] + d[1])
            if self._out_of_grid(next_state):
                next_state = state
            next_state_probs.setdefault(next_state, 0.0)
            next_state_probs[next_state] += prob

        npr = []
        for ns, prob in next_state_probs.items():
            next_grid_state = self._grid_state(ns)
            reward = self.terminal_reward if next_grid_state == 'goal' else self.non_terminal_reward
            npr.append((ns, prob, reward))

        return npr

    def step(self, state, action):
        npr = self.get_transition_probabilites_and_reward(state, action)
        probs = [t[1] for t in npr]
        sampled_idx = np.random.choice(range(len(npr)), p=probs)
        sampled_npr = npr[sampled_idx]
        next_state = sampled_npr[0]
        reward = sampled_npr[2]
        is_terminal = next_state == tuple(self.goal_location)
        return next_state, reward, is_terminal

def get_base_kwargs():
    goal_location = (9,9)
    action_stochasticity = [0.8, 0.2/3, 0.2/3, 0.2/3]
    grey_out = [(3,2), (4,2), (5,2), (6,2)]
    brown_in = [(9,7)]
    grey_in = [(0,0)]
    brown_out = [(1,7)]
    non_terminal_reward = 0
    terminal_reward = 10

    base_kwargs =  {"goal_location": goal_location, 
            "action_stochasticity": action_stochasticity,
            "brown_in": brown_in, 
            "grey_in": grey_in, 
            "brown_out": brown_out,
            "non_terminal_reward": non_terminal_reward,
            "terminal_reward": terminal_reward,
            "grey_out": grey_out,}
    
    return base_kwargs

base_kwargs = get_base_kwargs()

def value_iteration(env, gamma):
    # Initial Values
    values = np.zeros((10, 10))

    # Initial policy
    policy = np.empty((10, 10), object)
    policy[:] = 'N' # Make all the policy values as 'N'

    # Begin code here
    value_grids = [];
    policies = [];
    deltas = [];
    
    tol = 1e-8
    
    while True:

        value_grids.append(values.copy())
        policies.append(policy.copy())

        J_old = values.copy()

        delta = 0

        # Max J(s) for all states
        for x1 in range(env.grid_size[0]):
            for x2 in range(env.grid_size[1]):
                s = (x1,x2)
                J_star = float('-inf')

                # Max action for J(s) given state s
                for a in env.perpendicular_order:
                    J_exp = 0
                    for t in env.get_transition_probabilites_and_reward(s,a):
                        ns, p, r = t

                        # Calculating expected reward for given action
                        J_exp += p*(r + gamma*J_old[ns[0],ns[1]])

                    if J_exp > J_star:
                        J_star = J_exp
                        a_star = a

                delta = max(delta,np.abs(J_star-J_old[x1,x2]))

                values[x1,x2] = J_star
                policy[x1,x2] = a_star      

        deltas.append(delta)
        
        if delta < tol:
            break

    value_grids.append(values.copy())
    policies.append(policy.copy())

    
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {
        "Values" : value_grids,
        "Policy": policies,
        "Diffs" : deltas
    }

    # End code

    # Do not change the number of output values
    return {"Values": values, "Policy": policy}, extra_info

import matplotlib.pyplot as plt

# Plotting and visualizing functions

def visualize(env, values, pol):
    x = list(range(10))
    y = list(range(10))

    X, Y = np.meshgrid(x,y)

    U = np.zeros((10,10))
    V = np.zeros((10,10))

    for x1 in range(10):
        for x2 in range(10):
            dir = pol[x1,x2]
            dir = env.actions.get(dir)

            U[x1][x2] = dir[1]
            V[x1][x2] = dir[0]

    # creating plot
    plt.figure(figsize = (6,6))
    im = plt.imshow(values, origin="lower", cmap = 'Oranges',vmax=10)
    plt.colorbar(im,fraction=0.046, pad=0.04)
    plt.quiver(X, Y, U, V, pivot = 'mid',color='k')
    plt.xticks(np.arange(-0.5,10)," ")
    plt.yticks(np.arange(-0.5,10)," ")
    plt.tick_params(which="both",bottom=False, left = False)
    plt.grid(True)

env = GridEnv_HW2(**base_kwargs)
res, extra_info = value_iteration(env, 0.7)

# Will be used later
Jv = res['Values'].copy()
extra_info_VI = extra_info.copy()

# The rounding off is just for making print statement cleaner
print(np.flipud(np.round(res['Values'], decimals=2)))
print(np.flipud(res['Policy']))

def policy_iteration(env, gamma):
    # Initial Values
    values = np.zeros((10, 10))

    # Initial policy
    policy = np.empty((10, 10), object)
    policy[:] = 'N' # Make all the policy values as 'N'

    # Begin code here   
    value_grids = [values.copy()]
    policies = [policy.copy()]
    
    tol = 1e-8
    
    while True:
        
        # Step 1 : Policy Evaluation
        while True:
            J_old = values.copy()
            delta = 0

            for x1 in range(env.grid_size[0]):
                for x2 in range(env.grid_size[1]):
                    s = (x1,x2)

                    # evaluation
                    a = policy[x1,x2]
                    J_exp = 0
                    for t in env.get_transition_probabilites_and_reward(s,a):
                        ns, p, r = t

                        # Calculating expected reward for given action
                        J_exp += p*(r + gamma*J_old[ns[0],ns[1]])

                    delta = max(delta,np.abs(J_exp-J_old[x1,x2]))

                    values[x1,x2] = J_exp    
            
            if delta < tol:
                break
                
        
        # Saving value grid and policies after every evaluation
        value_grids.append(values.copy())
        policies.append(policy.copy())
        
        # Step 2 : Policy Improvement
        J = values.copy()

        for x1 in range(env.grid_size[0]):
            for x2 in range(env.grid_size[1]):
                s = (x1,x2)
                J_star = float('-inf')

                # improvement
                for a in env.perpendicular_order:
                    J_exp = 0
                    
                    # evaluation exp J(x1,x2)
                    for t in env.get_transition_probabilites_and_reward(s,a):
                        ns, p, r = t

                        # Calculating expected reward for given action
                        J_exp += p*(r + gamma*J[ns[0],ns[1]])
                    
                    # print((x1,x2),a,J_exp)
                    
                    # argmax
                    if J_exp > J_star:
                        J_star = J_exp
                        a_star = a

                policy[x1,x2] = a_star
                

        # Break from main loop if policy converges
        if (policies[-1] == policy).all():
            break
    
    
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {
        "Values" : value_grids,
        "Policy": policies
    }

    # End code

    # Do not change the number of output values
    return {"Values": values, "Policy": policy}, extra_info

env = GridEnv_HW2(**base_kwargs)
res, extra_info = policy_iteration(env, 0.7)

# Will be used later
extra_info_PI = extra_info.copy()

 # The rounding off is just for making print statement cleaner
print(np.flipud(np.round(res['Values'], decimals=2)))
print(np.flipud(res['Policy']))

# The policy mentioned in the pdf to be used for TD lambda, do not modify this
def heuristic_policy(env, state):
    goal = env.goal_location
    dx = goal[0] - state[0]
    dy = goal[1] - state[1]
    if abs(dx) >= abs(dy):
        direction = (np.sign(dx), 0)
    else:
        direction = (0, np.sign(dy))
    for action, dir_val in env.actions.items():
        if dir_val == direction:
            target_action = action
            break
    return target_action

def td_lambda(env, lamda, seeds):
    alpha = 0.5
    gamma = 0.7
    N = len(seeds)
    # Usage of input_policy
    # heuristic_policy(env, state) -> action
    example_action = heuristic_policy(env, (1,2)) # Returns 'N' if goal is (9,9)

    # Example of env.step
    # env.step(state, action) -> Returns next_state, reward, is_terminal

    # Initial values
    values = np.zeros((10, 10))
    es = np.zeros((10,10))

    value_iter = [values.copy()]

    for episode_idx in range(N):
         # Do not change this else the results will not match due to environment stochas
        np.random.seed(seeds[episode_idx])
        grey_in_loc = np.where(env.grid == 'grey_in')
        state = grey_in_loc[0][0], grey_in_loc[1][0]
        done = False
        while not done:
            action = heuristic_policy(env, state)
            ns, rew, is_terminal = env.step(state, action) 
            # env.step is already taken inside the loop for you, 
            # Don't use env.step anywhere else in your code

            # Begin code here
            d = rew + gamma*values[ns] - values[state]
            es[state] += 1
            
            # Updating grid
            values = values.copy() + alpha*d*es.copy()
            es = gamma*lamda*es.copy()
            
            state = ns
            
            if is_terminal: # if ns is goal state
                done = True
        
        value_iter.append(values.copy())
                          
    # Put your extra information needed for plots etc in this dictionary
    extra_info = {"Values": value_iter}

    # End code

    # Do not change the number of output values
    return {"Values": values}, extra_info

env = GridEnv_HW2(**base_kwargs)
res, extra_info = td_lambda(env, lamda=0.5, seeds=np.arange(1000))

 # The rounding off is just for making print statement cleaner
print(np.flipud(np.round(res['Values'], decimals=2)))

# This cell is only for your subjective evaluation results, display the results as asked in the pdf
# You can change it as you require, this code should run TD lamdba by default for different values of lambda

lamda_values = np.arange(0, 100+5, 5)/100
td_lamda_results = {}
extra_info = {}
for lamda in lamda_values:
    env = GridEnv_HW2(**base_kwargs)
    td_lamda_results[lamda], extra_info[lamda] = td_lambda(env, lamda,
                                                           seeds=np.arange(1000))

def get_results(kwargs):

    gridenv = GridEnv_HW2(**kwargs)

    policy_iteration_results = policy_iteration(gridenv, 0.7)[0]
    value_iteration_results = value_iteration(gridenv, 0.7)[0]
    td_lambda_results = td_lambda(env, 0.5, np.arange(1000))[0]

    final_results = {}
    final_results["policy_iteration"] = policy_iteration_results
    final_results["value_iteration"] = value_iteration_results
    final_results["td_lambda"] = td_lambda_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):
    if 'Policy' in results:
        policy_match = results['Policy'] == targets['Policy']
    else:
        policy_match = True
    # Reference https://numpy.org/doc/stable/reference/generated/numpy.allclose.html
    rewards_match = np.allclose(results['Values'], targets['Values'], rtol=3)
    equal = rewards_match and policy_match
    return equal

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))

# Defining error function

def error(values, Jv):
    """
    Takes in a list of values at every iteration from extra_info and the values
    from VI as Jv ouputting the errors for each iteration as a list.
    """
    c = Jv.size
    res = []
    for J in values:
        err = np.sqrt(np.sum(np.square(J - Jv))/c)
        res.append(err)
    
    return res

# Plotting curves

values = extra_info_PI['Values']
y = error(values, Jv)

plt.figure(figsize = (12,7))
plt.xlabel('Outer-loop iterations $(i)$',fontsize=14)
plt.ylabel('$error(J^i)$',fontsize=14)

plt.plot(list(range(len(y))), y)
plt.xlim(0,len(y)-1)
plt.show()

# Plotting curves
from scipy.signal import savgol_filter

lamda_list = [0, 0.25, 0.5, 0.75, 1]

values = {}
y = {}

plt.figure(figsize = (12,7))
plt.xlabel('Episodes $(i)$',fontsize=14)
plt.ylabel('$error(J^i)$',fontsize=14)

for lamda in lamda_list:
    values[lamda] = extra_info[lamda]["Values"].copy()

    # Using a Savitzky-Golay filter for smoother plots
    y[lamda] = savgol_filter(error(values[lamda].copy(), Jv),101,3)

    # printing mean
    print(np.round(np.mean(y[lamda]),decimals=4))

    plt.plot(list(range(len(y[lamda]))), y[lamda], label = '$\lambda =$' + str(lamda))

plt.legend(fontsize=14)
plt.xlim(0, len(y[lamda])-1)
plt.show()

!DATASET_PATH=$AICROWD_DATASET_PATH aicrowd notebook submit --no-verify -c iit-m-rl-assignment-2-gridworld -a assets