Project 4 - QLearning

Gridworld

Introduction

In this lab, you will construct the code to qlearning and utilize epsilon greedy within this framework. The basis for lab were developed as part of the Berkerly AI (http://ai.berkeley.edu) project.

Files

• pacmanQLearning.zip in a directory. In this PA, you will be changing the qlearningAgents.py file.

The value iteration agent that you implemented in the last PA does not actually learn from experience. Rather, it ponders its MDP model to arrive at a complete policy before interacting with a real environment. When it does interact with the environment, it simply follows the precomputed policy (e.g. it becomes a reflex agent). This distinction may be subtle in a simulated environment like a Gridword, but it’s very important in the real world, where the real MDP T and R functions are not available.

Part 1: QLearning

You will now write a Q-learning agent, which does very little on construction, The agent instead learns by trial and error from interactions with the environment through its update(state, action, nextState, reward) function. A stub of a Q-learner is specified in QLearningAgent in qlearningAgents.py. When you run the model you can select it with the option -a q.

For this portion of the assignment, you must implement the following functions within qlearningAgents.py:

• init (init some class variables that you might need)
• update
• computeValueFromQValues
• getQValue
• computeActionFromQValues

Note: For computeActionFromQValues, you should break ties randomly for better behavior. The random.choice() function will help. In a particular state, actions that your agent hasn’t seen before still have a Q-value, specifically a Q-value of zero, and if all of the actions that your agent has seen before have a negative Q-value, an unseen action may be optimal.

With the Q-learning update in place, you can watch your Q-learner learn under manual control, using the keyboard:

python gridworld.py -a q -k 5 -m

Recall that -k will control the number of episodes your agent gets during the learning phase. Watch how the agent learns about the state it was just in, not the one it moves to, and “leaves learning in its wake.”

Hint: to help with debugging, you can turn off noise by using the –noise 0.0 parameter (though this obviously makes Q-learning less interesting). If you manually steer the Gridworld agent north and then east along the optimal path for 5 episodes using the following command (with no noise), you should see the following Q-values:

python gridworld.py -a q -k 5 -m --noise 0.0

Grading: We will run your Q-learning agent and check that it learns the same Q-values and policy as our reference implementation when each is presented with the same set of examples. To grade your implementation, run the autograder:

python autograder.py -q q1

Part 2: Epsilon Greedy

Complete your Q-learning agent by implementing the epsilon-greedy action selection technique in the getAction function. Your agent will choose random actions an epsilon fraction of the time, and follows its current best Q-values otherwise. Note that choosing a random action may result in choosing the best action - that is, you should not choose a random sub-optimal action, but rather any random legal action.

For this portion of the assignment, you must implement/augment the following function:

• getAction Implements Epsilon greedy.

HINTS:

• In python, You can choose an element from a list uniformly at random by calling the random.choice function.
• You can simulate a binary variable with probability p of success by using util.flipCoin(p), which returns True with probability p and False with probability 1-p.

After implementing the getAction method, observe the following behavior of the agent in gridworld (with epsilon = 0.3).

python gridworld.py -a q -k 100 

Your final Q-values should resemble those from your value iteration agent (Lab9), especially along well-traveled paths. However, your average returns will be lower than the Q-values predict because of the random actions and the initial learning phase.

You can also observe the following simulations for different epsilon values. Does that behavior of the agent match what you expect?

python gridworld.py -a q -k 100 --noise 0.0 -e 0.1
python gridworld.py -a q -k 100 --noise 0.0 -e 0.9

To test your implementation, run the autograder:

python autograder.py -q q2

Working with the Crawler

If your eplison grredy code is working, you can run the crawler simulation shown in class.

python crawler.py

If this doesn’t work, you’ve probably written some code too specific to the GridWorld problem and you should make it more general to all MDPs.

This command above invokes the crawling robot from class using your Q-learner. Play around with the various learning parameters to see how they affect the agent’s policies and actions. Note that the step delay is a parameter of the simulation, whereas the learning rate and epsilon are parameters of your learning algorithm, and the discount factor is a property of the environment.

Crawler Report

Create a report that showcases the following items:

• How many steps did it take for your crawler to function (that is, crawl well)
• what values did you use for the eps, learning rate parameters. How/when/why did you change them during the simulation.

Part 3: Having Fun With Pacman (Optional)

Time to play some Pacman! Pacman will play games in two phases. In the first phase, training, Pacman will begin to learn about the values of positions and actions. Because it takes a very long time to learn accurate Q-values even for tiny grids, Pacman’s training games run in quiet mode by default, with no GUI (or console) display. Once Pacman’s training is complete, he will enter testing mode. When testing, Pacman’s self.epsilon and self.alpha will be set to 0.0, effectively stopping Q-learning and disabling exploration, in order to allow Pacman to exploit his learned policy. Test games are shown in the GUI by default. Without any code changes you should be able to run Q-learning Pacman for very tiny grids as follows:

python pacman.py -p PacmanQAgent -x 2000 -n 2010 -l smallGrid

Note that PacmanQAgent is already defined for you in terms of the QLearningAgent you’ve already written. PacmanQAgent is only different in that it has default learning parameters that are more effective for the Pacman problem (epsilon=0.05, alpha=0.2, gamma=0.8). You will receive full credit for this question if the command above works without exceptions and your agent wins at least 80% of the time. The autograder will run 100 test games after the 2000 training games.

Hint: If your QLearningAgent works for gridworld.py and crawler.py but does not seem to be learning a good policy for Pacman on smallGrid, it may be because your getAction and/or computeActionFromQValues methods do not in some cases properly consider unseen actions. In particular, because unseen actions have by definition a Q-value of zero, if all of the actions that have been seen have negative Q-values, an unseen action may be optimal. Beware of the argmax function from util.Counter!

Note: If you want to experiment with learning parameters, you can use the option -a, for example -a epsilon=0.1,alpha=0.3,gamma=0.7. These values will then be accessible as self.epsilon, self.gamma and self.alpha inside the agent.

Note: While a total of 2010 games will be played, the first 2000 games will not be displayed because of the option -x 2000, which designates the first 2000 games for training (no output). Thus, you will only see Pacman play the last 10 of these games. The number of training games is also passed to your agent as the option numTraining.

Note: If you want to watch 10 training games to see what’s going on, use the command:

python pacman.py -p PacmanQAgent -n 10 -l smallGrid -a numTraining=10

During training, you will see output every 100 games with statistics about how Pacman is faring. Epsilon is positive during training, so Pacman will play poorly even after having learned a good policy: this is because he occasionally makes a random exploratory move into a ghost. As a benchmark, it should take between 1000 and 1400 games before Pacman’s rewards for a 100 episode segment becomes positive, reflecting that he’s started winning more than losing. By the end of training, it should remain positive and be fairly high (between 100 and 350).

Make sure you understand what is happening here: the MDP state is the exact board configuration facing Pacman, with the now complex transitions describing an entire ply of change to that state. The intermediate game configurations in which Pacman has moved but the ghosts have not replied are not MDP states, but are bundled in to the transitions.

Once Pacman is done training, he should win very reliably in test games (at least 90% of the time), since now he is exploiting his learned policy.

However, you will find that training the same agent on the seemingly simple mediumGrid does not work well. In our implementation, Pacman’s average training rewards remain negative throughout training. At test time, he plays badly, probably losing all of his test games. Training will also take a long time, despite its ineffectiveness.

Pacman fails to win on larger layouts because each board configuration is a separate state with separate Q-values. He has no way to generalize that running into a ghost is bad for all positions. Obviously, this approach will not scale.

To test your implementation, run the autograder:

python autograder.py -q q3

Testing Your Code

You can test your implementation using manually driving around your agent commands from above and also using the following autograder command:

python autograder.py -q q1
python autograder.py -q q2

Part 3 is optional and is not graded.

Submission

Turn in the following items into Gradescope:

• qlearningAgents.py
• Craweler_report.pdf

Grading: