From 7d00a4a376294acce7cffc09ec2ec2d481709c53 Mon Sep 17 00:00:00 2001 From: Jens Ahrensfeld Date: Thu, 2 Jan 2020 21:26:07 +0000 Subject: [PATCH] - improved git-svn-id: http://moon:8086/svn/projects/RL-lab@343 fda53097-d464-4ada-af97-ba876c37ca34 --- rl_lab.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/rl_lab.py b/rl_lab.py index b93d72a..f1d7c52 100644 --- a/rl_lab.py +++ b/rl_lab.py @@ -71,9 +71,9 @@ def run(pos, N_trials, learning_rate, penalty_factor=0.99, forgetting_factor=0.9 # forget(forgetting_factor) - P = P_door[pos] - Pn = P/np.sum(P) + Pn = P_door[pos]/np.sum(P_door[pos]) + P_door[pos,:] *= forgetting_factor while True: fail = False door = choose_door(Pn) @@ -100,8 +100,7 @@ def run(pos, N_trials, learning_rate, penalty_factor=0.99, forgetting_factor=0.9 P_door[pos][door] *= penalty_factor continue else: - P[door] = P[door] + learning_rate - P_door[pos] = P + P_door[pos][door] = P_door[pos][door] + learning_rate break @@ -112,7 +111,7 @@ def run(pos, N_trials, learning_rate, penalty_factor=0.99, forgetting_factor=0.9 return moves_needed, lab_visited -for i in range(0, 1000): +for i in range(0, 100): moves_needed, lab_visited = run(pos=(0,0), N_trials=1000, learning_rate=0.5) print ('Visited map after {} moves:'.format(moves_needed)) # print (lab_visited)