n_rows = 4
n_columns = 4
obstacles = [(1,1), (2,2)]
s_size=1, a_size=4,h_size=32
lr=1e-2
n_training_episodes=1500, max_t=200, gamma=0.99
batches=20
alpha = 0.8

RESULT - 
16/20 converged
1/16 converged late
keeping the good cases and getting rid of others (keeping 20/20)