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.

127 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
0answers
841 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 ...
4
votes
1answer
97 views

How does the optimization process in hindsight experience replay exactly work?

I was reading the following research paper Hindsight Experience Replay. This is the paper that introduces a concept called Hindsight Experience Replay (HER), which basically attempts to alleviate the ...
4
votes
1answer
123 views

What could be the cause of the drop in the reward in A3C?

The mean episodic reward is generally increasing, but it has spontaneous drops, and I'm not sure of their cause. The problem has a sparse reward, batch size=2000, <...
4
votes
0answers
436 views

What could be causing the drastic performance drop of the DQN model on the Pong environment?

I am running a basic DQN (Deep Q-Network) on the Pong environment. Not a CNN, just a 3 layer linear neural net with ReLUs. It seems to work for the most part, but at some point, my model suffers from ...
4
votes
1answer
169 views

How did the OpenAI 5 for Dota concatenate units?

I am no expert in the field of AI so I apologize if this is a simple/easy question. I was trying to implement a network similar to OpenAI's for another game and I noticed that I did not fully ...
4
votes
1answer
134 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 ...
4
votes
1answer
2k views

How to deal with different actions for different states of the environment?

I'm new to this AI/Machine Learning and was playing around with OpenAI Gym a bit. When looking through the environments, I came across the Blackjack-v0 environment, ...
3
votes
0answers
94 views

How to deal with a moving target in the Lunar Lander environment with DDPG?

I have noticed that DDPG does rather well at solving environments with a static target. For example, the default of Lunar Lander, the flags do not change position. So the DDPG model learns how to get ...
3
votes
0answers
72 views

Where does this variation of the importance sampling weight come from?

I have seeing a variation in importance sampling (IS) in Prioritized Experience Replay (PER) in some implementations regarding the original paper approach stated as (in section 3.4): $$ w_{i}=\left(\...
3
votes
0answers
83 views

How to take actions at each episode and within each step of the episode in deep Q learning?

In deep Q learning, we execute the algorithm for each episode, and for each step within an episode, we take an action and record a reward. I have a situation where my action is 2-tuple $a=(a_1,a_2)$. ...
3
votes
0answers
72 views

Understanding the TensorFlow implementation of the policy gradient method

I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow. I think I got almost everything. The only thing that still bothers me is the loss function ...
3
votes
0answers
55 views

How does normalization of the inputs work in the context of PPO?

What does the normalization of the inputs mean in the context of PPO? At each time step of an episode, I only know the values of this time step and of the previous ones, if I take track of them. This ...
3
votes
0answers
692 views

How much time does it take to train DQN on Atari environment?

I am trying to build a DQN model for the Atari Pong game, but I am not sure whether the model is learning at all. I am using the architecture described in the paper Playing Atari with Deep ...
3
votes
0answers
160 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 ...
3
votes
0answers
58 views

Is this a good approach to solving Atari's “Montezuma's Revenge”?

I'm new to Reinforcement Learning. For an internship, I am currently training Atari's "Montezuma's Revenge" using a double Deep Q-Network with Hindsight Experience Replay (HER) (see also ...
3
votes
0answers
43 views

How to deal with nonstationary rewards in asymmetric self-play reinforcement learning?

Suppose we're training two agents to play an asymmetric game from scratch using self play (like Zerg vs. Protoss in Starcraft). During training one of the agents can become stronger (discover a good ...
3
votes
0answers
180 views

Deep Q-Network (DQN) to learn the game 2048

I am trying to build a Deep Q-Network (DQN) agent that can learn to play the game 2048. I am orientating myself on other programs and articles that are based on the game snake and it worked well (...
3
votes
0answers
30 views

Training a reinforcement learning model with multiple images

I am tentatively trying to train a deep reinforcement learning model the maze escaping task, and each time it takes one image as the input (e.g., a different "maze"). Suppose I have about $10K$ ...
3
votes
0answers
236 views

DQN Agent not learning anymore - what can I do to fix this?

I am trying to use Deep-Q-Learning to learn an ANN which controls a 7-DOF robotic arm. The robotic arm must avoid an obstacle and reach a target. I have implemented a number of state-of-art ...
3
votes
0answers
52 views

Deep Q-Learning agent poor performing actions. Need help optimizing

I'm trying to make deep q-learning agent from https://keon.io/deep-q-learning My environment looks like this: https://imgur.com/a/OnbiCtV As you can see my agent is a circle and there is one gray ...
3
votes
0answers
188 views

What can be considered a deep recurrent neural network?

In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the DRQN is described as DQN with the first post-convolutional fully-connected layer replaced by a recurrent LSTM. I have DQN ...
2
votes
0answers
29 views

How to prove Lemma 1.6 in the book “Reinforcement Learning: Theory and Algorithms”

I am trying to prove the following lemma from Reinforcement Learning: Theory and Algorithms on page 8. Lemma 1.6. We have that: $$ \left[(1-\gamma)\left(I-\gamma P^{\pi}\right)^{-1}\right]_{(s, a),\...
2
votes
1answer
37 views

How does sharing parameters between the policy and value functions help in PPO?

The PPO objective may include a value function error term when parameters are shared between the policy and value functions. How does this help, and when to use a neural network architecture that ...
2
votes
0answers
94 views

Update Rule with Deep Q-Learning (DQN) for 2-player games

I am wondering how to correctly implement the DQN algorithm for two-player games such as Tic Tac Toe and Connect 4. While my algorithm is mastering Tic Tac Toe relatively quickly, I cannot get great ...
2
votes
0answers
26 views

What is the name of this algorithm that estimates the gradient with an average by sampling from a distribution?

Consider maximizing the function $R(w)$ with parameter $w$ using gradient ascent. However, we don't know the gradient $\nabla_wR(w)$ formula. Now suppose $w$ is sampled from a probability distribution ...
2
votes
1answer
47 views

How can I compress the states of a reinforcement learning agent?

I'm working on a problem that involves an RL agent with very large states. These states consist of several pieces of information about the agent. The states are not images, so techniques like ...
2
votes
0answers
71 views

Is (log-)standard deviation learned in TRPO and PPO or fixed instead?

After having read Williams (1992), where it was suggested that actually both the mean and standard deviation can be learned while training a REINFORCE algorithm on generating continuous output values, ...
2
votes
0answers
20 views

Can DQN outperform DoubleDQN?

I found a similar post about this issue, but unfortunately I did not find a proper answer. Are there any references where DQN is better than DoubleDQN, that is DoubleDQN does not improve DQN ?
2
votes
0answers
77 views

Policy gradient: Does it use the Markov property?

To derive the policy gradient, we start by writing the equation for the probability of a certain trajectory (e.g. see spinningup tutorial): $$ \begin{align} P_\theta(\tau) &= P_\theta(s_0, a_0, ...
2
votes
0answers
42 views

Is Deep SARSA learning a feasible approach?

I noticed that SARSA has been rarely used in the deep RL setting. Usually, the training for DQN is done off-policy. I think one of the major reasons for this is due to greater sample efficiency in ...
2
votes
0answers
40 views

How to combine two differently equally important signals into the reward function, that have different scales?

I have two signals that I want to use to model my reward. The first one is the CPU TIME: running mean from this diagram: The second one is the MAX RESIDUAL from this diagram: Since they are both ...
2
votes
0answers
100 views

If the minimum Q value is decreasing and the maximum Q value increasing, is this a sign that dueling double DQN is diverging?

I'm training a dueling double DQN agent with prioritized replay buffer and notice that the min Q values are decreasing, while the max Q values are increasing. Is this a sign that it is diverging? ...
2
votes
0answers
78 views

How can the target rely on untrained parameters?

I'm trying to understand DQN. I understand where the loss function comes from. I'm just unsure about why the target function works in practice. Given the loss function $$ L_i(\theta_i) = [(y_i - Q(s,a;...
2
votes
0answers
48 views

Are the final states not being updated in this $n$-step Q-Learning algorithm?

I am reading this paper and in algorithm 3 they describe an $n$-step Q-Learning algorithm. Below is the pseudo-code. From this pseudo-code, it looks as though the final tuples that they would ...
2
votes
0answers
79 views

How to prevent deep Q-learning algorithms to overfit?

I have recently solved the Cartpole problem using double deep Q-learning. When I saw how the agent was doing, it used to go right every time, never left, and it did similar actions all the time. Did ...
2
votes
0answers
38 views

Can you find another reason for sample inefficiency of model-free on-policy Deep Reinforcement Learning?

The following mindmap gives an overview of multiple reasons for sample inefficiency. The list is definitely not complete. Can you see another reason not mentioned so far? Some related links: ...
2
votes
0answers
68 views

Does the concept of validation loss apply to training deep Q networks?

In deep learning, the concept of validation loss is to ensure that the model being trained is not currently overfitting the data. Is there a similar concept of overfitting in deep q learning? Given ...
2
votes
0answers
304 views

Why is it hard to prove the convergence of the deep Q-learning algorithm?

Why is it hard to prove the convergence of the DQN algorithm? We know that the tabular Q-learning algorithm converges to the optimal Q-values, and with a linear approximator convergence is proved. ...
2
votes
0answers
75 views

NaNs after a while in training of PPO

My problem is that every time I am trying to train my PPO agent I get NaN values after a while. The diagnostic that I get is the following: ...
2
votes
0answers
34 views

How was the DQN trained to play many games?

Some people claim that DQN was used to play many Atari games. But what actually happened? Was DQN trained only once (with some data from all games) or was it trained separately for each game? What was ...
2
votes
0answers
169 views

How does adding noise to the action in DDPG help in learning?

I can't understand how playing with the action generated by the actor network in DDPG by adding the noise term helps in exploration.
2
votes
0answers
53 views

Torch CNN not training

I am completely new to CNN's, and I do not quite know how to design or use them efficiently. That being said, I am attempting to build a CNN that learns to play Pac-man with reinforcement learning. I ...
2
votes
0answers
58 views

How does the TRPO surrogate loss account for the error in the policy?

In the Trust Region Policy Optimization (TRPO) paper, on page 10, it is stated An informal overview is as follows. Our proof relies on the notion of coupling, where we jointly define the ...
2
votes
0answers
247 views

Why overfitting is bad in DQN?

It is mentioned by Fu 2019 that overfitting might have a negative effect on training DQN. They showed that with either early stopping or experience replay this effect could be reduced. The first is ...
2
votes
0answers
168 views

Why experience reply memory in DQN instead of a RNN memory?

I was trying to implement a DQN without experience reply memory, and the agent is not learning anything at all. I know from readings that experience reply is used for stabilizing gradients. But how ...
2
votes
0answers
46 views

How does Hindsight Experience Replay cope with multiple goals?

What if there are multiple goals? For example, let's consider the bit-flipping environment as described in the paper HER with one small change: now, the goal is not some specific configuration, but ...
1
vote
1answer
28 views

How do I represent sample efficiency of RL rewards in mathematical notation?

I define sample efficiency as the area under the curve/graph, where $x$-axis is the number of episodes while y-axis is the cumulative reward for that episode. I would like to formally define it with a ...
1
vote
0answers
19 views

Recommended literature on layers for reinforcement learning

I was recommended to ask here after I posted on stack overflow wrongly. I was wondering if anyone had any recommended readings on layers used in neural networks for reinforcement learning? I've been ...
1
vote
0answers
14 views

Are there guiding principles as to which activation functions suit a given RL algorithm?

Are there rules of thumb as to which activation functions work well (or which one would not) on the policy and value network of a class of RL algorithms? For hidden layers and for the output layer. ...
1
vote
0answers
20 views

Is there any thumb rule on the cardinality of state space in order to use the parameterized function to estimate value functions?

Value functions for a given MDP can be learned in at least two ways by experience. The first way (tabular calculation) is generally used in the case of state spaces that are small enough. The second ...