I'm trying to solve a reinforcement learning problem with a simple q learning algorithme. I must add a new state to my table if the agent don't already know it. The probleme I have is that when I learn the new state, I have the folowing error: 'None of [x] are in the [index]'
I did a little test code to understand what's happening and solve the problems when I encounter one but I don't find solution to this one.
Here's my code:
import pandas as pd import numpy as np import random actions = [0, 1] obs = (0) q_table = pd.DataFrame(columns=actions) def check_state_exist(state): global q_table if state not in q_table.index: # append new state to q table q_table = q_table.append( pd.Series( [0]*len(actions), index=q_table.columns, name=state, ) ) def choose_action(state): global actions check_state_exist(state) # action selection if np.random.uniform() < 0.9: # choose best action state_action = q_table.loc[state, :] state_action = state_action.reindex(np.random.permutation(state_action.index)) # some actions have same value action = np.argmax(state_action) else: # choose random action action = np.random.choice(actions) return action for i in range(50): rand = random.randrange(100) if rand == 1: obs = 'rare' else: obs = [rand, random.randrange(10)] obs = tuple(obs) choose_action(obs) 'None of [(56, 5)] are in the [index]'
print(q_table) 0 1 (56, 5) 0 0 Thanks for your help
