TaxiDriverGym

In [ ]:

import random
from IPython.display import clear_output
import gymnasium as gym
import numpy as np
from QLearning import QLearning
from numpy import loadtxt

import random from IPython.display import clear_output import gymnasium as gym import numpy as np from QLearning import QLearning from numpy import loadtxt

In [ ]:

env = gym.make("Taxi-v3", render_mode='ansi').env

env = gym.make("Taxi-v3", render_mode='ansi').env

In [ ]:

# only execute the following lines if you want to create a new q-table
qlearn = QLearning(env, alpha=0.1, gamma=0.99, epsilon=0.7, epsilon_min=0.05, epsilon_dec=0.99, episodes=50000)
q_table = qlearn.train('data/q-table-taxi-driver.csv', 'results/actions_taxidriver')
#q_table = loadtxt('data/q-table-taxi-driver.csv', delimiter=',')

# only execute the following lines if you want to create a new q-table qlearn = QLearning(env, alpha=0.1, gamma=0.99, epsilon=0.7, epsilon_min=0.05, epsilon_dec=0.99, episodes=50000) q_table = qlearn.train('data/q-table-taxi-driver.csv', 'results/actions_taxidriver') #q_table = loadtxt('data/q-table-taxi-driver.csv', delimiter=',')

In [ ]:

(state, _) = env.reset()
epochs, penalties, reward = 0, 0, 0
done = False
frames = [] # for animation

(state, _) = env.reset() epochs, penalties, reward = 0, 0, 0 done = False frames = [] # for animation

In [ ]:

while (not done) and (epochs < 100):
    action = np.argmax(q_table[state])
    state, reward, done, t, info = env.step(action)

    if reward == -10:
        penalties += 1

    # Put each rendered frame into dict for animation
    frames.append({
        'frame': env.render(),
        'state': state,
        'action': action,
        'reward': reward
        }
    )
    epochs += 1

while (not done) and (epochs < 100): action = np.argmax(q_table[state]) state, reward, done, t, info = env.step(action) if reward == -10: penalties += 1 # Put each rendered frame into dict for animation frames.append({ 'frame': env.render(), 'state': state, 'action': action, 'reward': reward } ) epochs += 1

In [ ]:

from IPython.display import clear_output
from time import sleep

from IPython.display import clear_output from time import sleep

In [ ]:

clear_output(wait=True)

clear_output(wait=True)

In [ ]:

def print_frames(frames):
    for i, frame in enumerate(frames):
        clear_output(wait=True)
        print(frame['frame'])
        #print(frame['frame'].getvalue())
        print(f"Timestep: {i + 1}")
        print(f"State: {frame['state']}")
        print(f"Action: {frame['action']}")
        print(f"Reward: {frame['reward']}")
        sleep(.1)

def print_frames(frames): for i, frame in enumerate(frames): clear_output(wait=True) print(frame['frame']) #print(frame['frame'].getvalue()) print(f"Timestep: {i + 1}") print(f"State: {frame['state']}") print(f"Action: {frame['action']}") print(f"Reward: {frame['reward']}") sleep(.1)

In [ ]:

print_frames(frames)

print_frames(frames)

In [ ]:

print("\n")
print("Timesteps taken: {}".format(epochs))
print("Penalties incurred: {}".format(penalties))

print("\n") print("Timesteps taken: {}".format(epochs)) print("Penalties incurred: {}".format(penalties))