Skip to content

Tests: RL.py #450

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
norvig merged 2 commits into from
Apr 17, 2017
Merged

Tests: RL.py #450

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dbe9bda
Added test_rl.py
antmarakis Mar 30, 2017
6961ae4
Update test_rl.py
antmarakis Apr 1, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 55 additions & 0 deletions tests/test_rl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
import pytest

from rl import *
from mdp import sequential_decision_environment


north = (0, 1)
south = (0,-1)
west = (-1, 0)
east = (1, 0)

policy = {
(0, 2): east, (1, 2): east, (2, 2): east, (3, 2): None,
(0, 1): north, (2, 1): north, (3, 1): None,
(0, 0): north, (1, 0): west, (2, 0): west, (3, 0): west,
}



def test_PassiveADPAgent():
agent = PassiveADPAgent(policy, sequential_decision_environment)
for i in range(75):
run_single_trial(agent,sequential_decision_environment)

# Agent does not always produce same results.
# Check if results are good enough.
assert agent.U[(0, 0)] > 0.15 # In reality around 0.3
assert agent.U[(0, 1)] > 0.15 # In reality around 0.4
assert agent.U[(1, 0)] > 0 # In reality around 0.2



def test_PassiveTDAgent():
agent = PassiveTDAgent(policy, sequential_decision_environment, alpha=lambda n: 60./(59+n))
for i in range(200):
run_single_trial(agent,sequential_decision_environment)

# Agent does not always produce same results.
# Check if results are good enough.
assert agent.U[(0, 0)] > 0.15 # In reality around 0.3
assert agent.U[(0, 1)] > 0.15 # In reality around 0.35
assert agent.U[(1, 0)] > 0.15 # In reality around 0.25


def test_QLearning():
q_agent = QLearningAgent(sequential_decision_environment, Ne=5, Rplus=2,
alpha=lambda n: 60./(59+n))

for i in range(200):
run_single_trial(q_agent,sequential_decision_environment)

# Agent does not always produce same results.
# Check if results are good enough.
assert q_agent.Q[((0, 1), (0, 1))] >= -0.5 # In reality around 0.1
assert q_agent.Q[((1, 0), (0, -1))] <= 0.5 # In reality around -0.1