Newest 'q-learning' Questions

0

votes

0answers

7 views

Wich activation function for DQL

After many research, I still can't find a neat answer about this question: When I found the loss of my state-action pair. I'm only backpropagating that loss true the network and setting all other ...

asked Jun 17 at 12:26

Alexandre Martens

1

0

votes

1answer

25 views

Is this a valid stability concern/improvement for DQN/DDQN reinforcement training?

As you all know, DQN or DDQN are known for "unstable training". Let's use the well known "CartPole". The agent has to balance the stick and gets a reward of +1 per frame. You can reach the 195 ...

reinforcement-learning q-learning dqn

asked Jun 4 at 22:31

laz

32 bronze badges

0

votes

1answer

34 views

How to save and load a Q-Learning Agent

I know this may sound nooby, but how do I save a Deep Q-Learning agent's progress? I mean when I close at i.e. episode 500 when my agent is trained and I restart (in my case a pygame) my agent is ...

python training q-learning

asked May 21 at 12:06

Marc Vana

31 bronze badge

0

votes

0answers

24 views

First Simple DQN not learning to navigate maze

So I am currently attempting to write my first DQN implementation, where the aim is for the agent to learn to navigate the board from the top left to the bottom right while avoiding the hole right in ...

neural-network deep-learning reinforcement-learning q-learning

asked May 8 at 17:34

Krothagon

112 bronze badges

0

votes

0answers

17 views

Can we use Q-Learning (or RL in general) for this problem?

Let's say that we have an algorithm that given a dataset point, it runs some analysis on it and returns the results. The algorithm has a user-defined parameter X that affects the run-time of the ...

machine-learning reinforcement-learning q-learning

asked May 5 at 15:35

Omid

1

0

votes

0answers

9 views

Reward Function for a model-free MDP

I am trying to build a program which has to decide in a completely stochastic environment. So it has to be model-free and Q-learning is suitable for that. I just have one problem, my rewards are not ...

reinforcement-learning q-learning

asked Apr 23 at 6:49

Ammar

1

0

votes

0answers

8 views

For off policy reinforcement learning how different can the current policy be from the policies which generated the data

Say we have two policies and we use one to generate data with. We now want to use this data to optimize the second policy (the two policies are defined with the same input and output space but with ...

deep-learning reinforcement-learning q-learning policy-gradients

asked Apr 22 at 21:50

Azerila

1011 bronze badge

0

votes

0answers

5 views

Reward engineering to replace single terminal reward (exponential utility of terminal wealth)

My goal is to use reinforcement learning to train the agent (the trader) to maximize the exponential utility of his P&L (profit and loss) at a terminal time T. Therefore the natural formulation of ...

reinforcement-learning optimization q-learning discounted-reward

asked Apr 21 at 11:06

BGa

1

0

votes

0answers

20 views

How are n dimensional vectors state vectors represented in Q Learning?

Using this code: ...

reinforcement-learning beginner q-learning

asked Apr 14 at 19:46

blue-sky

1957 bronze badges

1

vote

0answers

58 views

Reward(t) vs. Reward(t+1) ? Reinforcement Learning, Q-learning

In "Reinforcement Learning, An Introduction; Richard S. Sutton and Andrew G. Barto" is written on page 70: 3.1 The Agent–Environment Interface At each time step t, the agent receives some ...

reinforcement-learning q-learning

asked Mar 19 at 1:59

anna12345

212 bronze badges

0

votes

0answers

48 views

Index tensor must have same dimensions as input tensor

I am trying to train a DQN to do optimal energy scheduling. Each state comes as a vector of 4 variables (represented by floats) saved in the replay memory as a state tensor, each action is an integer ...

deep-learning reinforcement-learning q-learning dqn

asked Mar 17 at 20:29

EArwa

356 bronze badges

1

vote

0answers

85 views

Q-learning, state transition, immediate rewards (trading logic)

I've been thinking about how to correctly calculate rewards for several weeks now. Here is a grid example: ...

python reinforcement-learning q-learning dqn

asked Mar 16 at 5:53

anna12345

212 bronze badges

0

votes

0answers

16 views

find the parameter of model with Q learning

I have a question with regard to Q learning. I am a beginner in Q learning. Every example that I saw is related to the environment that the goal is assigned to a place. (like cliff walk that we know ...

reinforcement-learning q-learning learning

asked Mar 2 at 17:44

Hasan

11 bronze badge

2

votes

0answers

18 views

Markov Decision Process representation

I'm attempting to model a simple process using a Markov Decision Process. Let $A$ be a set of $3$ actions : $ A \in \{b,s\}$. $T(s,a,s')$ represents the probability of if in state $s$ , take action $...

machine-learning reinforcement-learning q-learning markov-process

asked Feb 9 at 15:07

blue-sky

1957 bronze badges

1

vote

0answers

16 views

help understanding deep Q learning algorithm from deep mind paper

I'm studying this paper https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf, and I have a question about proposed algorithm(it appears on page 7 of the paper): The problem I see is ...

q-learning

asked Feb 3 at 15:03

burer

111 bronze badge

0

votes

1answer

18 views

How is the target_f updated in the Keras solution to the Deep Q-learning Cartpole/Gym algorithm?

There's a popular solution to the CartPole game using Keras and Deep Q-Learning: https://keon.github.io/deep-q-learning/ But there's a line of code that's confusing, this same question has been asked ...

deep-learning keras reinforcement-learning q-learning openai-gym

asked Feb 1 at 13:17

David Goudet

31 bronze badge

2

votes

2answers

111 views

Deep Q Network gives same Q values and doesn't improve

I'm trying to build a deep Q network to play snake. I've run into an issue where the agent doesn't learn and its performance at the end of the training cycle is to repeatedly kill itself. After a bit ...

python deep-learning keras reinforcement-learning q-learning

asked Dec 30 '19 at 22:10

achandra03

494 bronze badges

2

votes

1answer

101 views

Would Deep Q Learning work for a finite horizon problem?

I want to apply Deep Q Learning to a problem, which has a clear finite horizon definition, like: $$V(s) = \mathbb{E}[r_1 + r_2]$$ Since the horizon is finite, I do not use reward discounting. My ...

deep-learning reinforcement-learning q-learning dqn

asked Dec 26 '19 at 21:32

Ufuk Can Bicici

2031 silver badge5 bronze badges

2

votes

0answers

31 views

Incentivizing curiosity in a sparse reward environment

I'm quite new to reinforcement learning, but have been exploring different kinds of architectures (DQN, dueling DQN, actor critic, etc.) and evaluating their ability to solve certain problems. The ...

machine-learning neural-network deep-learning reinforcement-learning q-learning

asked Dec 14 '19 at 19:07

jhfa

611 bronze badge

1

vote

0answers

18 views

Deep Q Learning - training slows down significantly

I'm trying to build a deep Q network to play snake. I designed the game so that the window is 600 by 600 and the snake's head moves 30 pixels each tick. I implemented the DQN algorithm with memory ...

machine-learning python reinforcement-learning q-learning

asked Nov 29 '19 at 2:51

achandra03

494 bronze badges

0

votes

0answers

19 views

What reinforcement learning algorithm to choose for self-driving car

I have a car that has three sensors at the front. Using these sensors only I want to let it learn to drive on a track. I'm new to reinforcement learning, but I was thinking about using the Q-learning ...

machine-learning reinforcement-learning q-learning

asked Nov 22 '19 at 8:58

Zarif

101

0

votes

0answers

25 views

Applying Reinforcement Learning in the following scenario

I'm working on a scenario/environment where I have a simulation that provides an arrangement or results of the simulation that has data in a format of samples in vectors(x,y,z,N). Let's say it maps ...

reinforcement-learning q-learning markov-process

asked Nov 18 '19 at 14:06

RandomGuest

1

0

votes

0answers

85 views

Reducing the training time of an RL agent

I am trying to develop an rl agent using DQN algorithm.During training, the agent interacts with environment which is a simulated one.Each episode takes around 10 mins to run. This way if want my ...

reinforcement-learning q-learning dqn policy-gradients dynamic-programming

asked Sep 19 '19 at 8:34

cvg

4271 silver badge12 bronze badges

0

votes

0answers

53 views

Prioritized Experience Replay - for whole episodes

I want to use Prioritized Experience Replay for whole episodes, instead for single transitions. What's the best way to define the priorities - as episodes can be of different lengths? Personally I ...

machine-learning reinforcement-learning q-learning

asked Sep 19 '19 at 0:37

ScientiaEtVeritas

1417 bronze badges

1

vote

1answer

50 views

How to formulate reward of an rl agent with two objectives

I have started learning reinforcement learning and trying to apply it for my use case. I am developing an rl agent which can maintain temperature at a particular value, and minimize the energy ...

reinforcement-learning q-learning dqn monte-carlo discounted-reward

asked Sep 17 '19 at 8:36

cvg

4271 silver badge12 bronze badges

1

vote

0answers

37 views

Keras high loss and high accuracy in gk bot with reinforcement learning?

I'm making goal-keeper bot in haxball game. It worked well when i trained less but i worked worse when i trained more. Last reinforcement state: 5160 episode - 4171281 steps - 0.05 epsilon: Last fit ...

python deep-learning keras reinforcement-learning q-learning

asked Sep 5 '19 at 17:40

SolutionLover

111 bronze badge

1

vote

1answer

107 views

Q-learning when minimising a total cost instead of maximising a total reward

I have a decision problem where the results are measured as a cost that I want to minimise. It seems like a good fit to Q-learning, but I am not sure how to adjust it to deal with a cost instead of a ...

reinforcement-learning q-learning markov-process

asked Jul 30 '19 at 12:14

EArwa

356 bronze badges

0

votes

1answer

58 views

Deep Q-Learning for physical quantity: q-values distribution not as expected

Setting I am trying to learn a specific physical quantity (radiance) inside a 3D scene with Deep Q-Learning. Just to give a quick overview, my agent shoots rays inside the scene: the reward is the ...

deep-learning reinforcement-learning q-learning dqn

asked Jul 29 '19 at 9:24

maurock

2342 silver badges9 bronze badges

0

votes

0answers

22 views

What's the relationship amoung Temporal Difference and Policy Gradient, Deep Q learning?

I've gone through some comparisons between MC and TD to estimate $V_{\pi_\theta}(s)$. However, it seems to be not only a method to estimate V, but also a mechanism that can improve the update ...

machine-learning reinforcement-learning q-learning policy-gradients

asked Jul 22 '19 at 10:46

KningTG

111 bronze badge

1

vote

1answer

24 views

Why can't Policy Gradient Algorithm be seen as an Actor-Critic Method?

During the equation deducing in policy gradient algorithm(e.g., REINFORCE), we are actually using an expectancy of total reward, which we try to maximize. $$\overline{R_\theta}=E_{\tau\sim\pi_\theta}[...

machine-learning reinforcement-learning q-learning policy-gradients actor-critic

asked Jul 22 '19 at 9:54

KningTG

111 bronze badge

1

vote

1answer

390 views

DQN - target values vs action values?

I'm trying to understand the difference between target-values and action-values in Deep Q Networks. From what I understand, action-value tries to approximate the reward of a given action (at some ...

deep-learning reinforcement-learning q-learning

asked Jul 21 '19 at 17:42

Alter

1234 bronze badges

5

votes

1answer

450 views

Why could my DDQN get significantly worse after beating the game repeatedly?

I've been trying to train a DDQN to play OpenAI Gym's CartPole-v1, but found that although it starts off well and starts getting full score (500) repeatedly (at around 600 episodes in the pic below), ...

python deep-learning reinforcement-learning q-learning openai-gym

asked Jul 20 '19 at 8:06

Danny Tuppeny

1535 bronze badges

1

vote

1answer

229 views

Q table creation and update for dynamic action space

I am trying to implement a Q-learning algorithm for energy optimization. It is a finite MDP with states represented as 6 dimensional vectors of integers. The number of discrete values in each index of ...

q-learning

asked Jul 16 '19 at 14:41

EArwa

356 bronze badges

1

vote

2answers

347 views

Alternative approach for Q-Learning

I have a question related to an alterative Q-Learning approach. I'd like to know if this already exists and I am not aware of it, or it doesn't exist because there are theoretical problems behind it. ...

machine-learning reinforcement-learning q-learning

asked Jun 22 '19 at 8:23

maurock

2342 silver badges9 bronze badges

1

vote

1answer

530 views

Difference between Dueling DQN and Double DQN?

I have read some articles, but still can not figure out the difference between the Dueling DQN and Double DQN? What exactly is the difference between them? Also, Does Dueling DQN need to be built on ...

reinforcement-learning q-learning dqn deep-network

asked May 31 '19 at 17:46

Edamame

1,7454 gold badges12 silver badges21 bronze badges

2

votes

0answers

100 views

Reinforcement Learning using PPO2 in openai gym retro, mario not learning the clear the easy episode

I am training mario game in retro using ppo2 baselines for some time. I have tried level3 and level1 too. But even after full training when I play using saved checkpoints, the mario is not able to ...

reinforcement-learning q-learning openai-gym

asked May 11 '19 at 10:46

Sandeep Bhutani

4781 silver badge13 bronze badges

1

vote

0answers

68 views

Intuition behind the loss function in Deep Q learning?

I'm currently following a tutorial but I got stuck at the deep Q learning model. According to my understanding of neural networks they predict an approximate function for the inputs given with the ...

deep-learning reinforcement-learning loss-function q-learning

asked May 5 '19 at 12:34

anjani

112 bronze badges

2

votes

1answer

25 views

If the set of all possible states changes each time, how can Q-learning “learn” anything?

I found this resource that explains q-learning with a very simple example. Make it a 2D problem, a rectangle instead of a line, and it's still simple. The only difference is that now there are 2 more ...

reinforcement-learning q-learning

asked May 4 '19 at 21:40

Pigna

1633 bronze badges

2

votes

1answer

89 views

Representing state in Q-Learning

I have a fairly simple game in which I wish to use Q-learning to train an agent, but I have some questions regarding state representation. I'm new to RL so bare with me: If you have a game where you ...

reinforcement-learning beginner q-learning

asked May 4 '19 at 9:09

Ross Kohler

211 bronze badge

0

votes

1answer

699 views

Q-Learning experience replay: how to feed the neural network?

I'm trying to replicate the DQN Atari experiment. Actually my DQN isn't performing well; checking another one's codes, I saw something about experience replay which I don't understand. First, when you ...

python reinforcement-learning q-learning dqn keras-rl

asked Apr 11 '19 at 14:13

Joaquin

12 bronze badges

2

votes

1answer

519 views

DQN fails to find optimal policy

Based on DeepMind publication, I've recreated the environment and I am trying to make the DQN find and converge to an optimal policy. The task of an agent is to learn how to sustainably collect apples ...

reinforcement-learning q-learning dqn convergence deepmind

asked Apr 1 '19 at 1:23

macwiatrak

213 bronze badges

1

vote

0answers

20 views

Is reward accumulated during a play iteration when performing SARSA?

I've been having issue with getting my DQN to converge to a good solution for snake. Regardless of the different types of reward functions I've tried, it seems that the snake is indefinitely going ...

machine-learning deep-learning reinforcement-learning q-learning dqn

asked Mar 29 '19 at 1:44

DevarakondaV

314 bronze badges

0

votes

1answer

134 views

Openai Spaces for a modified environment

I have a 2-dimensional array of normalized data. I am using space = np.array([0,1,...366],[0,0.000001,.....1]) I need to fit this as an observation space in ...

python deep-learning reinforcement-learning q-learning openai-gym

asked Mar 17 '19 at 16:29

Karthik Rajkumar

656 bronze badges

1

vote

0answers

11 views

Q learning transition matrix trouble

First, apologies if this isn't the right forum for my question -- let me know if there's a better place. I'm trying to implement Q learning on a two-dimensional grid world, where the agent has four ...

machine-learning q-learning

asked Jan 30 '19 at 1:14

Elizabeth Han

1113 bronze badges

0

votes

1answer

58 views

Why is “next state” kept in RL experience replay?

Following this explanation on what is experience replay (and others), I noticed an experience element is defined as $e_t = (s_t,a_t,r_t,s_{t+1})$ My question is, why do we need the ...

machine-learning reinforcement-learning q-learning policy-gradients

asked Jan 23 '19 at 18:03

Gulzar

1338 bronze badges

1

vote

0answers

27 views

What is the meaning of the Variant Q-learning and To what INPUT and OUTPUT refer? in Abstract of DeepMind DQN paper 2013

-INPUT and OUTPUT OF ATARI DQN: In the abstract paragraph of the DQN work by DeepMind https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf it has written: " We present the first deep learning model to ...

deep-learning reinforcement-learning q-learning dqn deep-network

asked Jan 22 '19 at 10:36

user10296606

9561 gold badge4 silver badges18 bronze badges

2

votes

1answer

1k views

What is the difference between dynamic programming and Q-learning?

What is the difference between the DP-based algorithm and Q-learning?

reinforcement-learning q-learning dynamic-programming

asked Jan 21 '19 at 5:52

user10296606

9561 gold badge4 silver badges18 bronze badges

0

votes

1answer

84 views

How to represent an image as state in a Q-table

I'm trying to do Q-learning with the Atari games using the gym python's package. I want to use the image as the state of my algorithm, but I came up with a doubt: ...

reinforcement-learning q-learning openai-gym

asked Dec 31 '18 at 18:22

Neoares

1435 bronze badges

2

votes

1answer

89 views

How does Q-Learning deal with mixed strategies?

I'm trying to understand how Q-learning deals with games where the optimal policy is a mixed strategy. The Bellman equation says that you should choose $max_a(Q(s,a))$ but this implies a single unique ...

machine-learning reinforcement-learning q-learning

asked Dec 20 '18 at 17:48

Thomas Johnson

5451 gold badge3 silver badges11 bronze badges

1

vote

1answer

86 views

Why not use max(returns) instead of average(returns) in off-policy Monte Carlo control?

As I understand it, in reinforcement learning, off-policy Monte Carlo control is when the state-action value function $Q(s,a)$ is estimated as a weighted average of the observed returns. However, in ...

reinforcement-learning q-learning monte-carlo

asked Dec 20 '18 at 10:52

Meldgaard

112 bronze badges

Questions tagged [q-learning]

Related Tags