1faef74e7ddf364f30ed052c3a8b50ab919aa8a1,contents/4_Sarsa_lambda_maze/RL_brain.py,RL,choose_action,#RL#Any#,32

Before Change

        if np.random.rand() < self.epsilon:
            // choose best action
            state_action = self.q_table.loc[observation, :]
            state_action = state_action.reindex(np.random.permutation(state_action.index))     // some actions have same value
            action = state_action.idxmax()
        else:
            // choose random action
            action = np.random.choice(self.actions)
        return action

After Change

        // action selection
        if np.random.rand() < self.epsilon:
            // choose best action
            state_action = self.q_table.loc[observation, :]
            // some actions may have the same value, randomly choose on in these actions
            action = np.random.choice(state_action[state_action == np.max(state_action)].index)
        else:
            // choose random action
            action = np.random.choice(self.actions)
        return action

Instances