Contents

## How does DQN works?

DQN uses ϵ-greedy to select actions. It uses a greedy method to select actions from the Q-value function. But for the fully connected layers of the Q approximator, we add trainable parameterized noise below to explore actions.

## What is loss function in DQN?

Error or loss is measured as the difference between the predicted and actual result. In a DQN, we can represent our loss function as a squared error of the target Q value and prediction Q value.

## Why target network in DQN?

In DQN, a target network, which calculates a target value and is updated by the Q function at regular intervals, is introduced to stabilize the learning process. A less frequent updates of the target network would result in a more stable learning process.

## What is the target Q-value in dqns?

In a DQN, which uses off-policy learning, they represent a refined estimate for the expected future reward from taking an action a in state s, and from that point on following a target policy. The target policy in Q learning is based on always taking the maximising action in each state, according to current estimates of value.

## Why is the Q-loss not converging for DQN?

The Q-loss is calculated as MSE. Do you have ideas why the Q-loss is not converging? Does the Q-Loss have to converge for DQN algorithm? I’m wondering, why Q-loss is not discussed in most of the papers. Yes, the loss must coverage, because of the loss value means the difference between expected Q value and current Q value.

## When is the Q loss not converging in DeepMind?

In Deepmind’s 2015 DQN, the author clipped the gradient by limiting the value within [-1, 1]. In the other case, the author of Prioritized Experience Replay clip gradient by limiting the norm within 10. Here’re the examples: I think it’s normal that the Q-loss is not converging as your data keeps changing when your policy updates.

## What happens when Q value diverges in TensorFlow?

Only when loss value converges, the current approaches optimal Q value. If it diverges, this means your approximation value is less and less accurate. Maybe you can try adjusting the update frequency of the target network or check the gradient of each update (add gradient clipping).