Questions tagged [reinforcement-learning]

Area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward.

Filter by
Sorted by
Tagged with
0
votes
0answers
10 views

Reinforcement Learning, wont learn and bad in test set

I'm study and try to understand better the reinforcement learning branch; In this case I want to learn the agent to make a reward; I've tried with: A2C DQN PPO2 but the agent in test env make ever ...
0
votes
1answer
36 views

Deep Q-learning

I am working on the DDQN algorithm which is given in the following paper. I am facing a problem with the Q value. The author calculate Q value by this Q(s, a; θ , α, β) = V(s; θ , β) + A(s, a; θ , α). ...
0
votes
0answers
31 views

Can one use reinforcement learning to find a fixed point of a dynamical system?

I would like to know if it is possible to use reinforcement learning (RL) to find a fixed point of a dynamical system. By the fixed point, I mean $f(x)=x$. One can use Newton's method to get the fixed ...
0
votes
0answers
15 views

Q value is estimated under state V value and action A value for DDQN

How Q value is estimated under state V value and action A value. Given the below DDQN algorithm, the deep network is divided into two parts on the end layer, including state value function V(s) which ...
1
vote
1answer
38 views

Reinforcement Learning - after 800k timesteps agent wont learng

I'm study and try a reinforcement learning. now im using gym and stable-baseline. My project have a step where I calculate a reward with a function. -> step() -> calculate_reward() -> return ...
0
votes
0answers
6 views

Action signal gets saturated too quickly at DDPG

I am new to RL, so there might be some things that I miss here. My basic setup is like this: I have 60 observations and 15 actions, and I am trying to train a very nonlinear system with an DDPG agent, ...
0
votes
0answers
22 views

external input and Reinforcement Learning

Is there an RL method which in it the next state depends on the "current action" and "current state" AND an "External Input"?
0
votes
1answer
32 views

How does using another agents action choice impact the efficacy of learning with Deep Reinforcement Learning

I am doing a project where I have multiple soft actor-critic sub-agents learning at the same time in an environment using shared experiences. Each sub-agent selects an action using their own policy, ...
0
votes
1answer
29 views

Understanding DQN Algorithm

Im studying the deep q learning algorithm. You can see it in the picture here: DQN I have a few questions about the deep q learning algorithm. What do they mean with row 14: ...
0
votes
0answers
9 views

reinforcement learning , python, problem empty list

I'm trying to simulate a model, where a vehicle after having been in one destination then goes to the other on the list. The problem is that the list is empty. Someone help me? ...
0
votes
0answers
21 views

Where can I find real world examples of feature construction for reinforcement learning?

Since I am relatively new to the field of reinforcement learning and I read through the classic book Reinforcement Learning: An Introduction by Sutton et. al., in Chapter 9 the authors mention several ...
0
votes
0answers
6 views

Reinforcement Learning for distributing items on multiple places, i.e., scale balancing

I am interested in creating a reinforcement learning algorithm for assigning items to different buckets, such that the buckets are almost the same weight, i.e., scale but with more than two places to ...
0
votes
0answers
11 views

Usage of Chainer for Reinforcement Learning Purposes

I am trying toreplicate this code https://www.kaggle.com/prithviraj7387/deep-reinforcement-learning-on-stock-data used for Reinforcement Learning which is used for buying/selling stock I wanted to ...
1
vote
1answer
19 views

Is reinforcement learning suitable for the Dial-a-Ride problem?

Is reinforcement learning suitable for this problem or will it perform poorly against classical algorithms? "The Dial-a-Ride Problem (DARP) consists of designing vehicle routes and schedules for ...
0
votes
0answers
8 views

Algortihm for distributing volume in 1min stock intervals

Context: I have historical 1min prices for stocks, including premarket. However, when importing real-time data, the standard practice in the financial data industry is to give only OHLC (open, high, ...
0
votes
0answers
29 views

Am I using this neural network in a wrong way?

I'm trying to solve a RL problem; the Contextual Bandit problem using Deep Q Learning. My data is all simulated. I have this environment: ...
0
votes
0answers
10 views

How to deal with catastrophic forgetting?

I have my own implementation of ppo, which I've been trying to train for days on BreakoutNoFrameskip-v4 after totally failing to get a2c past a mean reward of 10 ...
0
votes
0answers
16 views

A2C 6M frames, and 2.5 hours of training on BreakoutNoFrameskip-v4 and a mean reward of 10

I've been trying for days to get A2C to work for BreakoutNoFrameskip-v4, I have my own implementation which I previously tested on PongNoFrameskip-v4 and it works ...
2
votes
1answer
45 views

Efficient way to tackle card games with many q-table states?

I'm currently in the process of developing an AI for a popular card game here in Germany (called "Schafkopf"). Obviously, one could try to find a perfect strategy with the help of some game ...
1
vote
0answers
19 views

Cartpole - Number of layers and neurons - model hyperparameters

Can anyone please suggest me how to arrive to the best optimal values for number of layers, number of neurons parameters of the deep learning model in DDQN algorithm for cartpole problem. As input and ...
1
vote
0answers
6 views

what is production selection probability in ACT-R?

I have a problem with declarative and production in instance based learning based on ACT-R. I have a dataset. each record is a instance with some features and label. I want to give payoff for final ...
0
votes
1answer
34 views

Solving Error: size mismatch, m1: [30 x 2], m2: [30 x 2]

I am getting the below error message: ...
0
votes
0answers
44 views

using Reinforcement learning for binary classification

I want to build an agent for binary classification. I have a large dataset with two label (0 and 1). I want to build an agent to predict labels. I build a deep model and now I want to build an agent. ...
0
votes
1answer
17 views

Can I set the rewards of a multi armed bandit problem with deterministic values?

I am new to reinforcement learning and I am tryng to understand the multi armed bandit problem. I think I have understood that it consists in choosing the bandit that maximizes the future reward. My ...
0
votes
0answers
18 views

Cannot train DQN to solve cartpole

This is the code of my DQN implementation. I have checked with codes in many other people's repositories. I cannot find any differences but it turns out my codes cannot train the model but theirs can. ...
0
votes
0answers
20 views

snake reinfocement learning does not learn

I’m new to reinf learning, and I’m trying this code, but the snake always goes right without learning, I can’t find the bug, could you help me? THE SNAKE CLASS ...
0
votes
0answers
15 views

Random exploration of an arbitrary agent (or dumb agent) in Deep RL

I'm trying to implement an agent in RL and I was wondering if it's pertinent to take random actions in DeepRL. I see that in traditional Q-learning that sometimes we take random actions to encourage ...
0
votes
0answers
14 views

Reinforcement Learning End Effector Moving To Camera and Stops Learning

I am working on training a 3 finger Jaw gripper. The environment I setup is this: UR10 3 finger robot Pybullet for Simulation Stable baselines and DDPG Observation space is RGB image stacked with ...
0
votes
0answers
45 views

Catastrophic Forgetting on DQN

I'm trying to explore solving the shortest path algorithm using DQN i know we can solve it using the Q-tablebut I just wanted to ...
0
votes
0answers
21 views

Deep-DQN implementation that works with (state,action) pairs

I'm moderately new to RL(Reinforcement learning) and trying to solve a problem by using a deep Q learning agent (trying a bunch of algorithms) and I don't want to implement my own agent (I would ...
0
votes
0answers
6 views

Model divergence in a pytorch TD3 implementation converted to tensorflow

Based on this implementation of TD3, I converted different torch-based methods to their tensorflow equivalents. No matter what hyperparameters I use, torch's version will start converging by 50,000 - ...
1
vote
0answers
23 views

Help in KERAS, a model.fit method on a array 50x50 slows the system, how can I make it faster?

i m a new member and i am a student. i have a problem. how can I make this training faster my neural network ? when I call the fit method on a 100 x 100 matrix goes very slow my model it's a ...
2
votes
2answers
33 views

Slow keras fit method with 100x100 array, how can I make it faster?

how can I make this training faster ? when I call the fit method on a 100 x 100 matrix goes very slow my model it's a sequential ...
0
votes
0answers
17 views

Should we sample z in VAE encoder during inference, when used in RL pipeline like World Models?

My question has been motivated by reading World Models by Ha and Schmidhuber. In shortcut, they introduce a RL framework where the current state (an image) is encoded via VAE into a latent vector $z$, ...
0
votes
0answers
9 views

In reinforcement learning, continue update weights after training?

Assuming an rl agent that has to be trained, and then you can mainain same weights over episodes: in a single episode, you have to firtly backup weights, udpate continuosly weights in the episodes, ...
0
votes
0answers
11 views

How to make fair comparison of multi-task RL models if I have unlimited test data?

The data comes from a simulator hence I have the possibility to generate unlimited data. The reward is 0 (no success) and success(1) if episode is successful. Now, the question is what metric to use ...
1
vote
1answer
37 views

In DQN, why not use target network to predict current state Q values?

In DQN, why not use target network to predict current state Q values, and not only next state q values? In doing a basic dq learning algorithm with nn from scratch, with replay memory, and minibatch ...
0
votes
0answers
114 views

Reinforcement Learning in continuing tasks (non-episodic)

I'm looking for an algorithm for Deep Reinforcement Learning in non-episodic or continuing tasks. To be explicit, I'm looking for an algorithm that allows the agent to learn online without separate ...
1
vote
0answers
25 views

DQN CartPole-v1 neural network doesn't optimize

I'm doing my first dnq algorithm, I'm trying to build a dnq agent, and neural network from scratch, but it seems that neural network doesn't optimize, I did 2 hidden layers, with ReLU, and the output ...
0
votes
1answer
41 views

Bellman operator and contraction property

Currently, I am learning about Bellman Operator in Dynamic Programming and Reinforcement Learning. I would like to know why is Bellman operator contraction with respect to infinity norm? Why not ...
2
votes
1answer
68 views

How to make our own environments for reinforcement learning?

How can we make our own environments for reinforcement learning? I have a heavy doubt that a game engine is used.. And if a game engine is used, which game engine is used that can be downloaded for ...
0
votes
1answer
29 views

Which Algorithm did OpenAI used to create a hide and seek playing Agent?

I just saw this video on youtube: https://www.youtube.com/watch?v=kopoLzvh5jY&t=9s Which Algorithm did OpenAI used to create a hide and seek playing Agent? Was it Genetic Algorithm or Policy ...
0
votes
1answer
100 views

Actor Network Target Value in A2C Reinforcement Learning

In DQN, we use; $Target = r+\gamma v(s')$ equation to train (fit) our network. It is easy to understand since we use the $Target$ value as the dependent variable like we do in supervised learning. I....
0
votes
0answers
16 views

How to use binary numbers and plain floats in the same neural network input for reinforcement learning?

I'm modeling a system whose configuration can be represented by a binary array ([1,0,0,1] or [0,1,0,0], for example), and the agent can move on a 2D space (thus having 3 DoFs), and the action the ...
2
votes
1answer
28 views

Which Policy Gradient Method was used by Google's Deep Mind to teach AI to walk

I just saw this video on Youtube. Which Policy Gradient method was used to train the AI to walk? Was it DDPG or D4PG or what?
0
votes
1answer
57 views

Difference between $Q(s,a)$ ,$V^*(s)$ and $V^\pi(s)$ in Markov Decision Process?

I am new to RL and I am trying to understand how to find solutions of an MDP. This is what I understand so far -> since the nature of our environment is stochastic, at a state 's' if we take an ...
0
votes
1answer
16 views

Why is DDPG a Policy Gradient Method? [closed]

Why is DDPG a Policy Gradient Method even though it's actor does not output probability?
0
votes
0answers
48 views

Q values loss per episode and mean absolute error

I am new to deep reinforcement learning! I am following this code for my adaptation problem (doing actions) https://github.com/jaromiru/AI-blog/blob/master/CartPole-DQN.py I am wondering how I can ...
2
votes
2answers
97 views

Is reinforcement learning a subset of unsupervised learning?

According to this article: Reinforcement learning on the other hand, which is a subset of Unsupervised learning ... How true is this statement? Is there any scholarly discussion/writing on the ...

1
2 3 4 5
11