!pip install aicrowd-cli > /dev/null

import os

AICROWD_DATASET_PATH = os.getenv("DATASET_PATH", os.getcwd()+"/5ed97a57-bc19-4f62-ae9e-f071d8b73317_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 =[]
    iter_length = 0
    tolerance = 10.0**-8
    extra_info = {}

    while True:
      iter_length +=1
      lenx,leny = values.shape
      for i in range(lenx):
          for j in range(leny):
              list_expected_value = []
              best_action = 0
              for action_id,action in enumerate(env.perpendicular_order):
                  action_outcomes = env.get_transition_probabilites_and_reward((i,j),action)
                  
                  expected_value_action = 0
                  for elt in action_outcomes:
                      #added discount to see if that was the issue
                      expected_value_action += elt[1]*(elt[2]+gamma*values[elt[0][0],elt[0][1]])
                  list_expected_value.append(expected_value_action)
                  if action_id !=0:
                      if expected_value_action> list_expected_value[best_action]:
                          best_action = action_id
      
              values[i,j] = list_expected_value[best_action]
              policy[i,j] = env.perpendicular_order[best_action]
      
      value_grids.append(np.copy(values))
      policies.append(np.copy(policy))
      extra_info[iter_length] =np.copy(values)
      if iter_length>1 and np.max(np.abs(value_grids[-1] - value_grids[-2]))<tolerance:
        break
      
    # Put your extra information needed for plots etc in this dictionary

    # 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 = value_iteration(env, 0.7)

 # 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   
    extra_info ={}
    done = 0
    count_iters = 0
    while done == 0:
      count_iters +=1
      delta = 1
      while delta>1e-8:
        delta = 0
        lenx,leny = values.shape
        for i in range(lenx):
            for j in range(leny):
              action = policy[i,j]
              action_outcomes = env.get_transition_probabilites_and_reward((i,j),action) 
              expected_value_action = 0
              for elt in action_outcomes:
                expected_value_action += elt[1]*(elt[2]+gamma*values[elt[0][0],elt[0][1]])

              delta = max(delta,np.abs(expected_value_action-values[i,j]))
              values[i,j] = expected_value_action


      done = 1
      for i in range(lenx):
        for j in range(leny):
          list_expected_value = []
          best_action = 0
          old_policy = policy[i,j]
          for action_id,action in enumerate(env.perpendicular_order):
            action_outcomes = env.get_transition_probabilites_and_reward((i,j),action)
            expected_value_action = 0
            for elt in action_outcomes:
              expected_value_action += elt[1]*(elt[2]+gamma*values[elt[0][0],elt[0][1]])
            list_expected_value.append(expected_value_action)
            if action_id !=0:
              if expected_value_action> list_expected_value[best_action]:
                best_action = action_id

          values[i,j] = list_expected_value[best_action]
          policy[i,j] = env.perpendicular_order[best_action]
          if policy[i,j] != old_policy:
            done=0
    
      extra_info[count_iters] = np.copy(values)

    # Put your extra information needed for plots etc in this dictionary

    # 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)

 # 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
    extra_info = {}
    values = np.zeros((10, 10))
    es = np.zeros((10,10))
    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
            
            delta = rew+gamma*values[ns[0],ns[1]]-values[state[0],state[1]]
            es[state[0],state[1]] +=1
            lenx,leny = values.shape
            for i in range(lenx):
              for j in range(leny):
                values[i,j] = values[i,j]+alpha*delta*es[i,j]
                es[i,j] = lamda*gamma*es[i,j]
   
            state = ns
            done=is_terminal
        extra_info[episode_idx] = np.copy(values)


              
    # Put your extra information needed for plots etc in this dictionary
    

    # 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.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, 25)/100
##This is changed from 0 to 100 in steps of 5 since that lead to timeout errrors.
td_lamda_results = {}
extra_info_td = {}
for lamda in lamda_values:
    env = GridEnv_HW2(**base_kwargs)
    print(lamda)
    td_lamda_results[lamda], extra_info_td[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))

import matplotlib.pyplot as plt
base_kwargs = get_base_kwargs()
env = GridEnv_HW2(**base_kwargs)
res_VI, extra_info_VI = value_iteration(env, 0.7)
res_PI, extra_info_PI = policy_iteration(env,0.7)

# final_error = [np.sqrt(np.sum(np.square(td_lamda_results[i]['Values']-res_VI['Values']))/100) for i in lamda_values]
# plt.figure(1)
# plt.plot(lamda_values,final_error)
# plt.title("Final Error as a function of $\lambda$")
# plt.xlabel("$\lambda$")
# plt.ylabel("Error")
# plt.show()

# bi,bo,gi = (base_kwargs['brown_in'][0],base_kwargs['brown_out'][0],base_kwargs['grey_in'][0])
# bi_val = [td_lamda_results[i]['Values'][bi[0],bi[1]] for i in lamda_values]
# bo_val = [td_lamda_results[i]['Values'][bo[0],bo[1]] for i in lamda_values]
# gi_val = [td_lamda_results[i]['Values'][gi[0],gi[1]] for i in lamda_values]


# plt.figure(1)
# plt.plot(lamda_values,bi_val,'r-')
# plt.plot(lamda_values,len(lamda_values)*[res_VI['Values'][bi[0],bi[1]]])
# plt.title("Value at Brown In as a function of $\lambda$")
# plt.xlabel("$\lambda$")
# plt.ylabel("Value at Brown In")
# plt.legend(("Expected","Actual (via VI)"))

# plt.figure(2)
# plt.plot(lamda_values,bo_val,'r-')
# plt.plot(lamda_values,len(lamda_values)*[res_VI['Values'][bo[0],bo[1]]])

# plt.title("Value at Brown Out as a function of $\lambda$")
# plt.xlabel("$\lambda$")
# plt.ylabel("Value at Brown Out")
# plt.legend(("Expected","Actual (via VI)"))

# plt.figure(3)
# plt.plot(lamda_values,gi_val,'r-')
# plt.plot(lamda_values,len(lamda_values)*[res_VI['Values'][gi[0],gi[1]]])
# plt.title("Value at Grey In as a function of $\lambda$")
# plt.xlabel("$\lambda$")
# plt.ylabel("Value at Grey In")
# plt.legend(("Expected","Actual (via VI)"))
# plt.show()

bi,bo,gi = (base_kwargs['brown_in'][0],base_kwargs['brown_out'][0],base_kwargs['grey_in'][0])

bi_val_VI = [extra_info_VI[i][bi[0],bi[1]] for i in extra_info_VI.keys()]
bo_val_VI = [extra_info_VI[i][bo[0],bo[1]] for i in extra_info_VI.keys()]
gi_val_VI = [extra_info_VI[i][gi[0],gi[1]] for i in extra_info_VI.keys()]

bi_val_PI = [extra_info_PI[i][bi[0],bi[1]] for i in extra_info_PI.keys()]
bo_val_PI = [extra_info_PI[i][bo[0],bo[1]] for i in extra_info_PI.keys()]
gi_val_PI = [extra_info_PI[i][gi[0],gi[1]] for i in extra_info_PI.keys()]

plt.figure(1)
plt.plot(bi_val_VI,'r-')
plt.plot(bi_val_PI,'b-')
plt.title("Estimated Value at Brown In as a function of iteration$")
plt.xlabel("Iterations")
plt.ylabel("Value at Brown In")
plt.legend(("VI","PI"))

plt.figure(2)
plt.plot(bo_val_VI,'r-')
plt.plot(bo_val_PI,'b-')
plt.title("Estimated Value at Brown Out as a function of iteration$")
plt.xlabel("Iterations")
plt.ylabel("Value at Brown Out")
plt.legend(("VI","PI"))

plt.figure(3)
plt.plot(gi_val_VI,'r-')
plt.plot(gi_val_PI,'b-')
plt.title("Estimated Value at Grey In as a function of iteration$")
plt.xlabel("Iterations")
plt.ylabel("Value at Grey In")
plt.legend(("VI","PI"))

plt.show()

final_error_PI = [np.sqrt(np.sum(np.square(extra_info_PI[i]-res_VI['Values']))/100) for i in extra_info_PI]
plt.figure(1)
plt.semilogy(final_error_PI)
plt.title("Final Error as a function of iteration, in PI")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()

final_error_TD0 = [np.sqrt(np.sum(np.square(extra_info_td[0.0][i]-res_VI['Values']))/100) for i in extra_info_td[0.0]]
final_error_TD25 = [np.sqrt(np.sum(np.square(extra_info_td[0.25][i]-res_VI['Values']))/100) for i in extra_info_td[0.25]]
final_error_TD50 = [np.sqrt(np.sum(np.square(extra_info_td[0.50][i]-res_VI['Values']))/100) for i in extra_info_td[0.50]]
final_error_TD75 = [np.sqrt(np.sum(np.square(extra_info_td[0.75][i]-res_VI['Values']))/100) for i in extra_info_td[0.75]]
final_error_TD100 = [np.sqrt(np.sum(np.square(extra_info_td[1.0][i]-res_VI['Values']))/100) for i in extra_info_td[1.0]]

plt.figure(1)
plt.plot(final_error_TD0)
plt.title("Final Error as a function of iteration, in TD(0)")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()
plt.figure(2)
plt.plot(final_error_TD25)
plt.title("Final Error as a function of iteration, in TD(0.25)")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()
plt.figure(3)
plt.plot(final_error_TD50)
plt.title("Final Error as a function of iteration, in TD(0.5)")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()
plt.figure(4)
plt.plot(final_error_TD75)
plt.title("Final Error as a function of iteration, in TD(0.75)")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()
plt.figure(5)
plt.plot(final_error_TD100)
plt.title("Final Error as a function of iteration, in TD(1)")
plt.xlabel("Iteration")
plt.ylabel("Error")
plt.show()

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