P1_DQN.py

import torch
import matplotlib.pyplot as plt
from unityagents import UnityEnvironment
import numpy as np
from collections import deque
from P1_agent import Agent

#replace with your own directory
env = UnityEnvironment(file_name="/home/arjun/Documents/Udacity/Deep_RL/deep-reinforcement-learning/p1_navigation/Banana_Linux/Banana.x86_64")

# get the default brain
brain_name = env.brain_names[0]
brain = env.brains[brain_name]
env_info = env.reset(train_mode=True)[brain_name]

agent = Agent(state_size=37, action_size=4, seed=0)


def dqn(n_episodes=500, max_t=10000, eps_start=0.5, eps_end=0.01, eps_decay=0.95):
    """Deep Q-Learning.

    Params
    ======
        n_episodes (int): maximum number of training episodes
        max_t (int): maximum number of timesteps per episode
        eps_start (float): starting value of epsilon, for epsilon-greedy action selection
        eps_end (float): minimum value of epsilon
        eps_decay (float): multiplicative factor (per episode) for decreasing epsilon
    """
    scores = []  # list containing scores from each episode
    scores_window = deque(maxlen=100)  # last 100 scores
    eps = eps_start  # initialize epsilon
    for i_episode in range(1, n_episodes + 1):
        env_info = env.reset(train_mode=True)[brain_name]
        state = env_info.vector_observations[0]
        score = 0
        for t in range(max_t):
            action = agent.act(state, eps)
            env_info = env.step(action)[brain_name]  # send the action to the environment
            next_state = env_info.vector_observations[0]  # get the next state
            reward = env_info.rewards[0]  # get the reward
            done = env_info.local_done[0]  # see if episode has finished

            agent.step(state, action, reward, next_state, done)
            state = next_state
            score += reward
            if done:
                break
        scores_window.append(score)  # save most recent score
        scores.append(score)  # save most recent score
        eps = max(eps_end, eps_decay * eps)  # decrease epsilon
        print('\rEpisode {}\tAverage Score: {:.2f}'.format(i_episode, np.mean(scores_window)), end="")
        if i_episode % 100 == 0:
            print('\rEpisode {}\tAverage Score: {:.2f}'.format(i_episode, np.mean(scores_window)))
        if np.mean(scores_window) >= 13.0:
            print('\nEnvironment solved in {:d} episodes!\tAverage Score: {:.2f}'.format(i_episode - 100,
                                                                                         np.mean(scores_window)))
            torch.save(agent.qnetwork_local.state_dict(), 'checkpoint.pth')
            break
    return scores


scores = dqn()

# plot the scores
fig = plt.figure()
ax = fig.add_subplot(111)
plt.plot(np.arange(len(scores)), scores)
plt.ylabel('Score')
plt.xlabel('Episode #')
plt.show()