Questions tagged [deep-rl]

For questions related to deep reinforcement learning (DRL), that is, RL combined with deep learning. More precisely, deep neural networks are used to represent e.g. value functions or policies.

Filter by
Sorted by
Tagged with
20 votes
2 answers
9k views

Are there other approaches to deal with variable action spaces?

This question is about Reinforcement Learning and variable action spaces for every/some states. Variable action space Let's say you have an MDP, where the number of actions varies between states (for ...
user avatar
19 votes
3 answers
3k views

Why doesn't Q-learning converge when using function approximation?

The tabular Q-learning algorithm is guaranteed to find the optimal $Q$ function, $Q^*$, provided the following conditions (the Robbins-Monro conditions) regarding the learning rate are satisfied $\...
user avatar
  • 33.8k
16 votes
1 answer
15k views

How does LSTM in deep reinforcement learning differ from experience replay?

In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the author processed the Atari game frames with an LSTM layer at the end. My questions are: How does this method differ from the ...
user avatar
15 votes
1 answer
4k views

Why does DQN require two different networks?

I was going through this implementation of DQN and I see that on line 124 and 125 two different Q networks have been initialized. From my understanding, I think one network predicts the appropriate ...
user avatar
12 votes
2 answers
5k views

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

Q-learning uses a table to store all state-action pairs. Q-learning is a model-free RL algorithm, so how could there be the one called Deep Q-learning, as deep means using DNN; or maybe the state-...
user avatar
  • 1,183
10 votes
2 answers
548 views

Was DeepMind's DQN learning simultaneously all the Atari games?

DeepMind states that its deep Q-network (DQN) was able to continually adapt its behavior while learning to play 49 Atari games. After learning all games with the same neural net, was the agent able to ...
user avatar
  • 203
9 votes
2 answers
1k views

What are the biggest barriers to get RL in production?

I am studying the state of the art of Reinforcement Learning, and my point is that we see so many applications in the real world using Supervised and Unsupervised learning algorithms in production, ...
user avatar
8 votes
2 answers
8k views

How large should the replay buffer be?

I'm learning DDPG algorithm by following the following link: Open AI Spinning Up document on DDPG, where it is written In order for the algorithm to have stable behavior, the replay buffer should ...
user avatar
8 votes
3 answers
2k views

How can you represent the state and action spaces for a card game in the case of a variable number of cards and actions?

I know how a machine can learn to play Atari games (Breakout): Playing Atari with Reinforcement Learning. With the same technique, it is even possible to play FPS games (Doom): Playing FPS Games with ...
user avatar
8 votes
1 answer
4k views

Suitable reward function for trading buy and sell orders

I am working to build a deep reinforcement learning agent which can place orders (i.e. limit buy and limit sell orders). The actions are ...
user avatar
  • 189
8 votes
1 answer
282 views

Is Experience Replay like dreaming?

Drawing parallels between Machine Learning techniques and a human brain is a dangerous operation. When it is done successfully, it can be a powerful tool for vulgarisation, but when it is done with no ...
user avatar
  • 571
8 votes
2 answers
745 views

Is reinforcement learning using shallow neural networks still deep reinforcement learning?

Often times I see the term deep reinforcement learning to refer to RL algorithms that use neural networks, regardless of whether or not the networks are deep. For example, PPO is often considered a ...
user avatar
  • 311
8 votes
2 answers
646 views

What is experience replay in laymen's terms?

I've been reading Google's DeepMind Atari paper and I'm trying to understand the concept of "experience replay". Experience replay comes up in a lot of other reinforcement learning papers (...
user avatar
7 votes
2 answers
401 views

What are some online courses for deep reinforcement learning?

What are some (good) online courses for deep reinforcement learning? I would like the course to be both programming and theoretical. I really liked David Silver's course, but the course dates from ...
user avatar
  • 81
7 votes
2 answers
5k views

How to combine backpropagation in neural nets and reinforcement learning?

I have followed a course on machine learning, where we learned about the gradient descent (GD) and back-propagation (BP) algorithms, which can be used to update the weights of neural networks, and ...
user avatar
  • 221
7 votes
2 answers
1k views

Where to publish a first article in Deep Reinforcement Learning?

What would be examples of journals that are good for a first publication in the field of Deep Reinforcement Learning? I am in the process of writing about the research results of DQN-related ...
user avatar
7 votes
1 answer
212 views

Why does reinforcement learning using a non-linear function approximator diverge when using strongly correlated data as input?

While reading the DQN paper, I found that randomly selecting and learning samples reduced divergence in RL using a non-linear function approximator (e.g a neural network). So, why does Reinforcement ...
user avatar
7 votes
2 answers
618 views

Is it possible to implement reinforcement learning using a neural network?

I've implemented the reinforcement learning algorithm for an agent to play snappy bird (a shameless cheap ripoff of flappy bird) utilizing a q-table for storing the history for future lookups. It ...
user avatar
7 votes
2 answers
1k views

Can DQN perform better than Double DQN?

I'm training both DQN and double DQN in the same environment, but DQN performs significantly better than double DQN. As I've seen in the double DQN paper, double DQN should perform better than DQN. Am ...
user avatar
  • 171
7 votes
0 answers
1k views

Is there a difference in the architecture of deep reinforcement learning when multiple actions are performed instead of a single action?

I've built a deep deterministic policy gradient reinforcement learning agent to be able to handle any games/tasks that have only one action. However, the agent seems to fail horribly when there are ...
user avatar
  • 403
6 votes
2 answers
1k views

Why is the log probability replaced with the importance sampling in the loss function?

In the Trust-Region Policy Optimisation (TRPO) algorithm (and subsequently in PPO also), I do not understand the motivation behind replacing the log probability term from standard policy gradients $$L^...
user avatar
  • 96
6 votes
2 answers
2k views

Do we have to use CNN for Deep Q Learning?

I read top articles on Google Search about Deep Q-Learning: https://medium.freecodecamp.org/an-introduction-to-deep-q-learning-lets-play-doom-54d02d8017d8 https://skymind.ai/wiki/deep-reinforcement-...
user avatar
  • 2,551
6 votes
1 answer
2k views

Can TD($\lambda$) be used with deep reinforcement learning?

TD lambda is a way to interpolate between TD(0) - bootstrapping over a single step, and, TD(max), bootstrapping over the entire episode length, or, Monte Carlo. Reading the link above, I see that an ...
user avatar
  • 669
6 votes
2 answers
141 views

Are there RL algorithms that also try to predict the next state?

So far I've developed simple RL algorithms, like Deep Q-Learning and Double Deep Q-Learning. Also, I read a bit about A3C and policy gradient but superficially. If I remember correctly, all these ...
user avatar
6 votes
1 answer
2k views

Should I be decaying the learning rate and the exploration rate in the same manner?

Should I be decaying the learning rate and the exploration rate in the same manner? What's too slow and too fast of an exploration and learning rate decay? Or is it specific from model to model?
user avatar
  • 91
6 votes
1 answer
761 views

Deep Q-Learning "catastrophic drop" reasons?

I am implementing some "classical" papers in Model Free RL like DQN, Double DQN, and Double DQN with Prioritized Replay. Through the various models im running on ...
user avatar
  • 61
6 votes
2 answers
602 views

Why don't people use projected Bellman error with deep neural networks?

Projected Bellman error has shown to be stable with linear function approximation. The technique is not at all new. I can only wonder why this technique is not adopted to use with non-linear function ...
user avatar
  • 490
6 votes
1 answer
95 views

In imitation learning, do you simply inject optimal tuples of experience $(s, a, r, s')$ into your experience replay buffer?

Due to my RL algorithm having difficulties learning some control actions, I've decided to use imitation learning/apprenticeship learning to guide my RL to perform the optimal actions. I've read a few ...
user avatar
  • 403
5 votes
3 answers
3k views

What is the target Q-value in DQNs?

I understand that in DQNs, the loss is measured by taking the MSE of outputted Q-values and target Q-values. What does the target Q-values represent? And how is it obtained/calculated by the DQN?
user avatar
  • 103
5 votes
2 answers
821 views

Is there any good reference for double deep Q-learning?

I am new in reinforcement learning, but I already know deep Q-learning and Q-learning. Now, I want to learn about double deep Q-learning. Do you know any good references for double deep Q-learning? ...
user avatar
5 votes
2 answers
493 views

Why AlphaGo didn't use Deep Q-Learning?

In the previous research, in 2015, Deep Q-Learning shows its great performance on single player Atari Games. But why do AlphaGo's researchers use CNN + MCTS instead of Deep Q-Learning? is that because ...
user avatar
  • 2,551
5 votes
2 answers
270 views

Is there an alternative to the use of target network?

In the context of Deep Q Network, a target network is usually utilized. The target network is a slow changing network with a changing rate as its hyperparameter. This includes both replacement update ...
user avatar
  • 490
5 votes
2 answers
2k views

What is the difference between DQN and AlphaGo Zero?

I have already implemented a relatively simple DQN on Pacman. Now I would like to clearly understand the difference between a DQN and the techniques used by AlphaGo zero/AlphaZero and I couldn't find ...
user avatar
5 votes
2 answers
3k views

How should I model all available actions of a chess game in deep Q-learning?

I just read about deep Q-learning, which is using a neural network for the value function instead of a table. I saw the example here: Using Keras and Deep Q-Network to Play FlappyBird and he used a ...
user avatar
  • 2,551
5 votes
1 answer
199 views

Clarifying representation of Neural Nerwork input for Chess Alpha Zero

In the Alpha Zero paper (https://arxiv.org/pdf/1712.01815.pdf) page 13, the input for the NN is described. In the beggining of the page, the authors state that: "The input to the Neural Network ...
user avatar
  • 63
5 votes
2 answers
317 views

Is it possible to guide a reinforcement learning algorithm?

I have just started to study reinforcement learning and, as far as I understand, existing algorithms search for the optimal solution/policy, but do not allow the possibility for the programmer to ...
user avatar
5 votes
1 answer
672 views

How do we compute the target value when the agent ends up in the terminal state?

I am working on a deep reinforcement learning problem. Throughout the episode, there is a small positive and negative reward for good or bad decisions. In the end, there is a huge reward for the ...
user avatar
  • 181
5 votes
2 answers
3k views

Why does self-playing tic-tac-toe not become perfect?

I trained a DQN that learns tic-tac-toe by playing against itself with a reward of -1/0/+1 for a loss/draw/win. Every 500 episodes, I test the progress by letting it play some episodes (also 500) ...
user avatar
  • 81
5 votes
1 answer
156 views

Why Q2 is a more or less independant estimate in Twin Delayed DDPG (TD3)?

Twin Delayed Deep Deterministic (TD3) policy gradient is inspired by both double Q-learning and double DQN. In double Q-learning, I understand that Q1 and Q2 are independent because they are trained ...
user avatar
5 votes
0 answers
226 views

How to correctly implement self-play with DQN?

I have an environment where an agent faces an equal opponent, and while I've achieved OK performance implementing DQN and treating the opponent as a part of the environment, I think performance would ...
user avatar
  • 51
5 votes
1 answer
321 views

Understanding multi-iteration updates of the model in the Proximal Policy Optimization algorithm

I have a general question about the updating of the network/model in the PPO algorithm. If I understand it correctly, there are multiple iterations of weight updates done on the model with data that ...
user avatar
4 votes
1 answer
1k views

Is there a machine learning model that can be trained with labels that only say how "right" or "wrong" it was?

I'm trying to find the name for a model that is used to output a decision (maybe something like right, left, or ...
user avatar
4 votes
1 answer
965 views

What are the major differences between multi-armed bandits and the other well-known algorithms (DQN, A3C, PPO, etc)?

I have studied in the past different algorithms, i.e. DQN, DDQN, REINFORCE, A3C, PPO, TRPO, so on. I am doing an internship this summer where I have to use a multi-armed bandit (MAB). I am a bit ...
user avatar
4 votes
1 answer
928 views

Mathematically, what is happening differently in the neural net during exploration vs. exploitation?

I want to understand roughly what is happening in the neural network of an RL agent when it is exploring vs. exploiting. For example, are the network weights not being updated when the agent is ...
user avatar
4 votes
3 answers
663 views

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem?

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem? For example, you want to train a DQN agent in an environment, and you want to know what the highest ...
user avatar
4 votes
1 answer
2k views

My DQN is stuck and can't see where the problem is

I'm trying to replicate the DeepMind paper results, so I implemented my own DQN. I left it training for more than 4 million frames (more than 2000 episodes) on SpaceInvaders-v4 (OpenAI-Gym) and it ...
user avatar
  • 153
4 votes
1 answer
2k views

How does the Ornstein-Uhlenbeck process work, and how it is used in DDPG?

In section 3 of the paper Continuous control with deep reinforcement learning, the authors write As detailed in the supplementary materials we used an Ornstein-Uhlenbeck process (Uhlenbeck & ...
user avatar
  • 41
4 votes
1 answer
472 views

What is the effect of parallel environments in reinforcement learning?

Do parallel environments improve the agent's ability to learn or does it not really make a difference? Specifically, I am using PPO, but I think this applies across the board to other algorithms too.
user avatar
4 votes
1 answer
263 views

Can a large discrete action space be represented using Gaussian distributions?

I have a large 1D action space, e.g. dim(A)=2000-10000. Can I use continuous action space where I could learn the mean and std of the Gaussian distributions that I would use to sample action from and ...
user avatar
  • 167
4 votes
1 answer
186 views

Are Q values estimated from a DQN different from a duelling DQN with the same number of layers and filters?

I am confused about the Q values of a duelling deep Q network (DQN). As far as I know, duelling DQNs have 2 outputs Advantage: how good it is to be in a particular state $s$ Value: the advantage of ...
user avatar
  • 41

1
2 3 4 5
9