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
1answer
31 views

How to write a reward function that optimizes for profit and revenue?

So I want to write a reward function for a reinforcement learning model which picks products to display to a customer. Each product has a profit margin %. Higher price products will have a higher ...
0
votes
0answers
17 views

How to train a policy and a value network, implementing alphazero at chess

So, I'm trying to implement alphazero's logic on the game of chess. What I understand so far of the algorithm is: Load 2 models, one of which is the best model you have so far. Both these models have ...
0
votes
0answers
8 views

Video games with built-in logging

I'd like to get some practice with reinforcement learning and data analysis in the domain of video games. I'm looking for a game that logs user behaviours (e.g. UI click events, player position, item ...
2
votes
1answer
18 views

Does GPU decreases training time for on-policy RL?

I was wondering whether using a GPU will be effective if I am using an on-policy (eg PPO) RL as the model? I.e, how can we use a GPU to decrease training time for an on-policy RL model? I recently ...
2
votes
1answer
37 views

Transferring the hidden state of a RNN to another RNN

I am using Reinforcement Learning to teach an AI an Austrian Card Game with imperfect information called Schnapsen. For different states of the game, I have different neural networks (which use ...
1
vote
1answer
20 views

Is it possible to optimize the Client Lifetime Value with Reinforcement Learning using Marketing Activities as Actions?

I have been researching the Reinforcement Learning topic. I have been looking if this is the correct way to optimize the marketing actions of my company given that we are looking to optimize the ...
1
vote
1answer
32 views

What approach should I take for my product classification ML model with user feedback for improving result accuracy?

I'm trying to implement a product categorization ML model on a dataset with the following structure: Data sample I want to my model to be able to predict the correct category that the product should ...
1
vote
0answers
10 views

How to create transition probability (state) for q-learning algorithm designed to control traffic light system using python?

I am trying to create a q learning algorithm to control traffic light systems. I am representing the state with a matrix : ...
0
votes
0answers
11 views

how to in enhance A3C entropy?

I'm trying to implement this A3C code in my custom environment, and I have a basic understanding of the algorithm. The algorithm worked, but it did not give me a good performance. I looked into ...
0
votes
0answers
9 views

How to draw Reward vs Episode Graph

I have just started learning reinforcement learning and I was following some tutorials on youtube. I found out out that no one was explaining how to draw reward vs episode graph. So I concluded that ...
0
votes
0answers
25 views

Which type of Reinforcement Learning to use?

First of all, I am new to the topic of machine learning, AI, etc. However, I would like to create a sophisticated decision algorithm. The decision is a Boolean decision and you can suppose the result ...
0
votes
0answers
35 views

Why is Pytorch 100x faster than Tensorflow for Deep Reinforcement Implementation?

[Intro] I am currently getting into machine learning coming from mathematics and am following a few courses to get the hang of this. In one of the courses, the author has a github with code examples: ...
0
votes
1answer
24 views

What problem can solve with reinforcement learning

I think classification problem cannot solve with reinforcement learning. I don't know what problem can solve with reinforcement learning. Is there a way to see if this problem can be solved with ...
1
vote
0answers
16 views

How to solve Bellman-Hamiltonian-Jacobi in stochastic environment through machine learning?

Suppose there is a stochastic optimal control problem where the uncertainty is because of the random arrival of entities into our system which is modelled as a Poisson process with rate $\lambda(p)$. ...
1
vote
0answers
15 views

Reinforcement learning with multiple agents

I am starting a project which involves multiple agents, some that play on the same team and others that play on the opponent's team. Since I am rather new to this topic, I did some research to get an ...
2
votes
0answers
28 views

Multi-arm bandits

I would like to model a problem as a multi-armed bandit problem. In the data we have contextual information (user demographics, preferences, etc.) but this contextual information of each user is not ...
0
votes
0answers
24 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
39 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
26 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
41 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
8 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
23 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
33 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
30 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
21 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
9 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
30 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
11 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
47 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
20 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
36 views

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

I am getting the below error message: ...
0
votes
0answers
60 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
21 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
50 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
22 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
7 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
18 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 $z$, ...

1
2 3 4 5
11