Andrei Cozma commited on
Commit
5aaffc4
·
1 Parent(s): 0c8eecb
policy_mc_CliffWalking-v0_e2000_s500_g0.99_e0.4.npy ADDED
Binary file (1.66 kB). View file
 
run_tests.py ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ import multiprocessing
3
+
4
+ vals_eps = [0.5, 0.4, 0.3, 0.2, 0.1, 0.05, 0.01]
5
+ vals_gamma = [1.0, 0.99, 0.98, 0.97, 0.95, 0.9, 0.8, 0.7, 0.5]
6
+
7
+ num_tests = 25
8
+
9
+
10
+ def run_test(args):
11
+ os.system(
12
+ f"python3 MonteCarloAgent.py --train --gamma {args[0]} --epsilon {args[1]} --wandb_project cs581 --wandb_job_type params"
13
+ )
14
+
15
+
16
+ with multiprocessing.Pool(8) as p:
17
+ p.map(run_test, [(gamma, eps) for gamma in vals_gamma for eps in vals_eps])