mm/mud-games
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

linting

Browse Source
This commit is contained in:
Michael Pilosov 2022-03-20 19:32:24 -06:00
parent 6020752d75
commit 53d2e1fdcb
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
main.py
View File

@ -10,19 +10,19 @@ from scipy.stats import norm
def train(data): def train(data):
D = pd.DataFrame(data) D = pd.DataFrame(data)
D['qoi'] = D['obs'].apply(lambda o: np.sum(o,axis=0)/np.sqrt(len(o))) D["qoi"] = D["obs"].apply(lambda o: np.sum(o, axis=0) / np.sqrt(len(o)))
D['i'] = D['lam'].apply(lambda l: norm.pdf(l).prod()) D["i"] = D["lam"].apply(lambda l: norm.pdf(l).prod())
D['o'] = D['qoi'].apply(lambda q: norm.pdf(q).prod()) D["o"] = D["qoi"].apply(lambda q: norm.pdf(q).prod())
Q = np.array(D['qoi'].to_list()).reshape(-1,4) Q = np.array(D["qoi"].to_list()).reshape(-1, 4)
K = [gkde(Q[:,i]) for i in range(4)] K = [gkde(Q[:, i]) for i in range(4)]
D['p'] = D['qoi'].apply(lambda q: np.prod([ K[i].pdf(q[i]) for i in range(4)])) D["p"] = D["qoi"].apply(lambda q: np.prod([K[i].pdf(q[i]) for i in range(4)]))
D['u'] = D['i']*D['o']/D['p'] D["u"] = D["i"] * D["o"] / D["p"]
mud_point_idx = D['u'].argmax() mud_point_idx = D["u"].argmax()
mud_point = D['lam'].iloc[mud_point_idx] mud_point = D["lam"].iloc[mud_point_idx]
return mud_point return mud_point
def test(decision=np.array([-0.09, -0.71, -0.43 , -0.74]), seed=1992): def test(decision=np.array([-0.09, -0.71, -0.43, -0.74]), seed=1992):
env = gym.make("CartPole-v1") env = gym.make("CartPole-v1")
observation, info = env.reset(seed=seed, return_info=True) observation, info = env.reset(seed=seed, return_info=True)
score = 0 score = 0
@ -42,7 +42,7 @@ def test(decision=np.array([-0.09, -0.71, -0.43 , -0.74]), seed=1992):
if __name__ == "__main__": if __name__ == "__main__":
data = pickle.load(open('data.pkl','rb')) data = pickle.load(open("data.pkl", "rb"))
mud_point = train(data) mud_point = train(data)
print(f"MUD Point: {mud_point}") print(f"MUD Point: {mud_point}")
test(mud_point) test(mud_point)