17
votes
Accepted
How does LSTM in deep reinforcement learning differ from experience replay?
How does this method differ from the experience replay, as they both use past information in the training? What's the typical application of both techniques?
Using a recurrent neural network is one ...
16
votes
Are there other approaches to deal with variable action spaces?
Does anyone know any paper regarding this subject?
I'm not familiar with any off the top of my head. I do know that the vast majority of Reinforcement Learning literature focuses on settings with a ...
13
votes
Why doesn't Q-learning converge when using function approximation?
Here's an intuitive description answer:
Function approximation can be done with any parameterizable function. Consider the problem of a $Q(s,a)$ space where $s$ is the positive reals, $a$ is $0$ or $...
13
votes
Accepted
Is there a machine learning model that can be trained with labels that only say how "right" or "wrong" it was?
What you are looking for is called "reinforcement learning".
A reinforcement learning algorithm will try to maximize a reward function. This reward represents how "good" or "...
12
votes
Accepted
Why does DQN require two different networks?
My best guess that it's been done to reduce the computation time, otherwise we would have to find out the q value for each action and then select the best one.
It has no real impact on computation ...
9
votes
Suitable reward function for trading buy and sell orders
Generally researchers (Ghandar et al, Michalewicz, Lam) have used the profit or return on investment (ROI) as a reward (fitness) function.
$ROI = \frac{ \left[\sum_{t=1}^T (Price_t - sc) \times I_s(t) ...
9
votes
Accepted
Do we have to use CNN for Deep Q Learning?
No. DQN and other deep RL methods work well with fully connected layers. Here's an implementation of DQN which doesn't use CNNs: github.com/keon/deep-q-learning/blob/master/dqn.py
DeepMind mostly use ...
9
votes
How large should the replay buffer be?
In order for the algorithm to have stable behavior, the replay buffer should be large enough to contain a wide range of experiences, but it may not always be good to keep everything.
The larger the ...
9
votes
What is the difference between Q-learning, Deep Q-learning and Deep Q-network?
Here is a table that attempts to systematically show the differences between tabular Q-learning (TQL), deep Q-learning (DQL), and deep Q-network (DQN).
Tabular Q-learning (TQL)
Deep Q-learning (DQL)
...
9
votes
Accepted
What are the major differences between multi-armed bandits and the other well-known algorithms (DQN, A3C, PPO, etc)?
You should start with the general definition of Reinforcement Learning problem. And what Markov Decision Process is.
DQN, A3C, PPO and REINFORCE are algorithms for solving reinforcement learning ...
8
votes
Accepted
Is Experience Replay like dreaming?
The speaker argued that a dream is a random addition of memories, just as experience replay.
The speaker is taking some liberties due to a general lack of scientific understanding of what dreams are. ...
8
votes
Accepted
How to combine backpropagation in neural nets and reinforcement learning?
Gradient descent and back-propagation
In deep learning, gradient descent (GD) and back-propagation (BP) are used to update the weights of the neural network.
In reinforcement learning, one could map (...
Community wiki
7
votes
Accepted
Can TD($\lambda$) be used with deep reinforcement learning?
Eligibility traces is a method of weighting between temporal-difference "targets" and Monte-Carlo "returns". In practice, for example, instead of using the one-step TD target, $r_t ...
7
votes
How large should the replay buffer be?
You need to read this 2020 paper by Deepmind:
"Revisiting Fundamentals of Experience Replay"
Also, to add to the answer by @nbro
Assume you implement experience replay as a buffer where the ...
7
votes
Why doesn't Q-learning converge when using function approximation?
As far as I'm aware, it is still somewhat of an open problem to get a really clear, formal understanding of exactly why / when we get a lack of convergence -- or, worse, sometimes a danger of ...
7
votes
Accepted
What are the biggest barriers to get RL in production?
There is a relatively recent paper that tackles this issue: Challenges of real-world reinforcement learning (2019) by Gabriel Dulac-Arnold et al., which presents all the challenges that need to be ...
7
votes
Accepted
Mathematically, what is happening differently in the neural net during exploration vs. exploitation?
Typically, the NN is trained the same way whether an action is chosen for exploration or exploitation. Look at the objective (AKA loss) function for any algorithm you're interested in and you'll ...
6
votes
Accepted
How should I model all available actions of a chess game in deep Q-learning?
To model chess as a Markov decision problem (MDP) you can refer to the AlphaZero paper (Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm). The exact details can ...
6
votes
Accepted
Should I be decaying the learning rate and the exploration rate in the same manner?
First of all, I'd say that there is a reason to give Learning Rate (LR) and Exploration Rate (ER) the same decay: they play at the same scale (the number of successive batches you'll train your model ...
6
votes
Why is the log probability replaced with the importance sampling in the loss function?
I am not 100% sure if the following is the only/complete story, but I'm quite confident it's at least part of the story:
In the PPO paper, after describing the standard policy gradient objective $L^{...
6
votes
Accepted
My DQN is stuck and can't see where the problem is
After some research and reading this post, I see where my problem was: I was introducing a full consecutive batch of experiences, selected randomly, yes, but the experiences in the batch were ...
6
votes
Accepted
What is the difference between DQN and AlphaGo Zero?
DQN and AlphaZero do not share much in terms of implementation.
However, they are based on the same Reinforcement Learning (RL) theoretical framework. If you understand terms like MDP, reward, return, ...
6
votes
Is there an alternative to the use of target network?
I have done some research and would like to share.
Generally to eliminate the use of target network one needs to show that training would be stable under off-policy semi-gradient.
There are two ...
6
votes
Accepted
What are some online courses for deep reinforcement learning?
Let me first say that deep RL is just the combination of RL with deep learning. So, if you study RL and deep learning, then studying deep RL should be straightforward. For this reason, this answer ...
6
votes
Accepted
Why AlphaGo didn't use Deep Q-Learning?
$Q$-learning (and also its deep variant, and most of the other well-known reinforcement learning algorithms) are inherently learning approaches for single-agent environments. The entire problem ...
6
votes
Accepted
Clarifying representation of Neural Nerwork input for Chess Alpha Zero
For anyone wondering, I believe to have found the answer:
Yes, it will be an 8x8 plane where all the entries are the same, the number of moves (or mpves with no progress).
There are two repetitions ...
5
votes
Accepted
Is the DQN only applicable with images as inputs?
More precisely: is DQNN applicable only when we have high translational invariance in our input(s)?
No, DQN is not restricted to images or other kinds of inputs with those properties, it can be used ...
5
votes
Accepted
When using experience replay, do we update the parameters for all samples of the mini-batch or for each sample in the mini-batch separately?
Gradient descent should be performed using the sum (or average) of the losses in the minibatch.
This is in fact also how I read the pseudocode in your question, though I understand it can be confusing....
5
votes
How can you represent the state and action spaces for a card game in the case of a variable number of cards and actions?
Instead of having the AI learn what action to take, you can alternatively train it to judge how "good" a position is. In order to determine what move to make, you don't ask the AI "This is the current ...
5
votes
Accepted
Understanding lemma 2 of the "Trust Region Policy Optimization" paper
We can start with equation (30):
$$
\bar{A}(s) = P(a \neq \tilde{a}) \mathbb{E}_{(a,\tilde{a})\sim(\pi,\tilde{\pi}|a\neq\tilde{a})} [A_\pi(s, \tilde{a}) - A_\pi(s, a)]
$$
Taking the absolute value ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
deep-rl × 406reinforcement-learning × 347
dqn × 135
q-learning × 74
deep-learning × 45
policy-gradients × 25
ddpg × 24
neural-networks × 21
experience-replay × 21
rewards × 17
proximal-policy-optimization × 16
actor-critic-methods × 15
machine-learning × 14
reference-request × 13
reward-functions × 13
double-dqn × 13
function-approximation × 12
alphazero × 12
action-spaces × 12
training × 10
reinforce × 10
ai-design × 9
game-ai × 9
markov-decision-process × 9
hyper-parameters × 9