n_rows = 5
n_columns = 5
obstacles = [(0, 1), (0, 3), (0,4)] 
s_size=1, a_size=4,h_size=32
lr=1e-2
n_training_episodes=2500, max_t=200, gamma=0.9
batches=20
alpha = 0.9

RESULT - 
6/20 converged
6/6 converged late
keeping the good cases and getting rid of others (keeping all)