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
1
vote
0answers
8 views

Actions taken by agentn/ agent performance not improving

Hi I am trying to develop an rl agent using PPO algorithm. My agent takes an action(CFM) to maintain a state variable called RAT in between 24 to 24.5. I am using PPO algorithm of stable-baselines ...
1
vote
1answer
35 views

Assistance needed on what machine learning approach to use

👋 I'm currently writing my Master's Thesis on Subjective tagging of sounds and I feel that I've been stuck with the same problem for quite a time now and need assistance to progress. I'll in short ...
1
vote
0answers
16 views

Cold-start problem in Real Time Bidding

I'm currently on the reading stage of the deployment of an RTB system. I've seen the problem of a cold start (having no initial guess of how to bid) in several papers, but I haven't really seen it be ...
3
votes
1answer
22 views

Why replay memory store old states and action rather than Q-value (Deep Q-learning)

Here is the algorithm use in Google's DeepMind Atari paper The replay memory D store transition (old_state, action performed, reward, new_state) The old_state and the performed action a are needed ...
1
vote
1answer
21 views

Idenitity between TD(0) algorithm and Policy Evaluation in Dynamic Programming when alpha is equal to 1

TD(0) algorithm is defined as the iterative update of the following: $$ V(s) \leftarrow V(s) + \alpha({r + \gamma V(s')} - V(s) ) $$ Now, if we assume alpha to be equal to 1, we get the traditional ...
2
votes
2answers
100 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 ...
4
votes
0answers
19 views

Reinforcement learning with sparse acting agent

I'm working on a problem where the optimal policy involves the agent "doing nothing" most of the time, and "doing something" during rare critical moments. Is there any literature or best practices ...
2
votes
1answer
53 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 ...
0
votes
0answers
25 views

Reinforcement Learning techniques to use if there is a direct connecction between (state, action) and reward

I want to build a model. The input state is a combination of different numbers in sequence (Their orders matter to the final result). The effectiveness of such number combination can be computed into ...
1
vote
0answers
18 views

How can I improve this tensorflow 2.0 function?

I recreated some code I found online for solving the bandits problem using policy gradient. The example was in tensorflow 1.0 so I recreated it with tensorflow 2.0 using eager execution and gradient ...
1
vote
1answer
16 views

Multiply Tensorflow sequential layer by fixed integers

I'm trying to make a simple reinforcement learning model that makes one of three decisions, A, B, or ...
0
votes
0answers
9 views

Vowpal Wabbit, Daemon mode “write error: Bad file descriptor”

I'm using the Vowpal Image provided by AWS @ amazonaws.com/sagemaker-rl-vw-container:vw-8.7.0-cpu. However, when I run Vowpal in daemon mode ...
0
votes
0answers
26 views

Why is orthogonal weights initialization so important for PPO?

I have implemented PPO to solve Atari environments. For the longest time I couldn't figure out why my model would not converge as fast as other open source solutions. Eventually it boiled down to this ...
2
votes
0answers
24 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 ...
1
vote
0answers
15 views

Reinforcement learning converges for mean loss but not for each training data

Here I show a dummy example that represents my actual problem. My neural network (NN) receives one input and gives the probabilities for two output nodes. The code for the NN is: ...
2
votes
1answer
18 views

reinforcement learning: Decompose a policy gradient

I am studying the policy gradient through the website: https://towardsdatascience.com/understanding-actor-critic-methods-931b97b6df3f Couldn't figure out how the first equation becomes the second ...
3
votes
1answer
32 views

Trouble understanding the partial differentiation used in reinforcement learning

I am studying deterministic actor-critic algorithms in reinforcement learning. I try to give a brief explanation of actor-critic algorithms before jumping into the mathematics. The actor takes in ...
6
votes
2answers
80 views

Actor-critic architecture: How is the policy updated?

I am going through the ddpg baseline code to try and gain an intuitive understanding of how the actor and critic networks function. DDPG has two components: the actor which is the deterministic ...
0
votes
0answers
16 views

Assumptions on discounted long-term loss

The infinite horizon discounted long-term loss is defined as: $$ f(\theta) = \mathbb{E}_{\tau \sim \mathbb{P}(.|\theta)}\left[\sum_{t=1}^{\infty}{\gamma^t l_m(s_t,a_t)}\right]$$ where $(s_t,a_t) \in ...
0
votes
0answers
12 views

exploitation vs. exploration: upper-confidence-bound vs. epsilon-greedy

I am looking into some different ways for doing exploitation vs. exploration (e.g. multi-arm bandit problem). There are approaches like upper_confidence_bound and epsilon-greedy. I am wondering what ...
0
votes
0answers
68 views

reinforcement learning: PPO vs. DDPG vs. TRPO - difference and intuition

I know there is a lot of blog talk about the PPO, DDPG and TRPO, but I am wondering would it be possible to explain the differences of these methods in layman's term? What's the intuition behind them ...
1
vote
0answers
11 views

Rewards are converged but with a lot of variations

I am training a reinforcement learning agent on an episodic task of fixed episode length. I am tracking the training process by plotting the cumulative rewards over an episode. I am using tensorboard ...
1
vote
0answers
14 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 ...
1
vote
0answers
9 views

Autonomous learning - chatbots

My chatbots need to be trained when we get new data or feedbacks from users. Can someone provides ways how these chatbots can learn on themselves and become intelligent day by day? Some of techniques ...
0
votes
1answer
24 views

Reinforcement Learning in NLP for chatbots

Is anyone aware of any successful implementation of reinforcement learning for NLP. I am looking to for chatbots which can learn automatically. Tried searching internet but found very few articles ...
0
votes
0answers
16 views

using reinforcement learning for classification

this is a purely conceptual query and in case the moderators feel it needs to be asked elsewhere, i would be happy to move it there. We do a lot of work in text classification and a senior ...
1
vote
1answer
24 views

Having a reward structure which gives high positive rewards compared to the negative rewards

I am training an RL agent using PPO algorithm for a control problem. The objective of the agent is to maintain temperature in a room. It is an episodic task with episode length of 9 hrs and step size(...
0
votes
0answers
11 views

DNN loss gets smaller but accuracy stays the same

I am learning a DeepNN to choose between three decisions in a simulation. Therefore, I can run the simulation as often as I want and can generate as many samples as I want. Based on this tutorial (...
1
vote
1answer
18 views

Formulation of a reward structure

I am new to reinforcement learning and experimenting with training of RL agents. I have a doubt about reward formulation, from a given state if a agent takes a good action i give a positive reward, ...
0
votes
0answers
10 views

Several dips in accumulated episodic rewardss during training of a reinforcement learning agent

Hi I am training reinforcement learning agents for a control problem using PPO algorithm. I am tracking the accumulated rewards for each episode during the training process. Several times during the ...
0
votes
0answers
23 views

Actor Critic Model implementation

I am going to work on a project which requires implementation of A2C model using Tensorflow 2.0. I am new in the Machine Learning field and also in Python. These are topics which I have covered ...
0
votes
0answers
6 views

two PPO implentations

I have uploaded here my PPO implentation from scratch: https://github.com/MakisKans/Reinforcement_Learning/tree/master/PPO In the PPO.py you can find two functions : learn and train. The former is ...
0
votes
0answers
17 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 ...
1
vote
1answer
33 views

Training a model that has both 2D and 1D features using a CNN

I'm looking to pre-train a model for an RL agent but I'm having some trouble figuring some stuff out. Dataset: Minerl MineRLNavigateDense-v0 The observation space includes : 2D screen input (64,64) ...
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 ...
0
votes
1answer
21 views

How to handle differences between training and deploying of an RL agent

Hi I am training an RL agent for a control problem. The objective of the agent is to maintain temperature in a zone. It is an episodic task with episode length of 10 hrs and actions being taken every ...
1
vote
0answers
21 views

How can I increase the speed and performance of my implementation of an AI for Reversi?

I made an AI for Reversi, aka Othello (8×8), like Alpha Zero, using this book. This book is written in Japanese. The source code of the AI I implemented can be found in this Github repository. There ...
0
votes
0answers
18 views

Prerequisites for reinforcement learning for DTR

I want to learn how RL is used for Dynamic Treatment Regimes. What are some must-read articles or papers? Also, I am relatively new to RL and am currently reading Sutton's book on the topic. Lets say ...
0
votes
0answers
16 views

saving a model during training of an RL agent

I am training an RL agent using PPO2 algorithm. Iam using stable-baselines library. During the training process, my rewards are slowly increasing and stabilizing, but are falling down suddenly. I ...
1
vote
0answers
36 views

DQN vs PG - when to use which?

I'd like to understand when using PG methods is more adequate than using DQN methods. Just to give a bit of background: I am currently using both APEX and R2D2 for my projects. Both work very well in ...
0
votes
0answers
46 views

Sudden decline in cumulative reward of an reinforcement learning training agent

Hi I am training an RL agent using PPO algorithm of stable baselines library. I have integrated my training with tensorboard to monitor the training process. Over a period of time my training rewards ...
0
votes
1answer
28 views

Different results every time I train a reinforcement learning agent

I am training an RL agent for a control problem using PPO algorithm. I am using stable-baselines library for it. The objective of an agent is to maintain a temperature of 24 deg in a zone and it ...
0
votes
0answers
12 views

Gym Cartpole not solving with Cross Entropy Method?

Cross Entropy Method is considered as one of the simplest optimization algorithm which can be used for training an agent. I tried to train an agent to solve gym's cartpole environment and I have used ...
0
votes
0answers
6 views

Why does my Deep Q Model only take a single action?

I don't know if this is the proper place to ask code-based questions on but I've been struggling with this issue for a while. Basically I am training a Deep Q Model using Keras and Google Colab (for ...
0
votes
0answers
10 views

How to use deep reinforcement learning to learn how to play Checkers?

I am a student new in reinforcement learning and I'm trying to implement an AI able to play Checkers. I want to implement a deep learning solution. However, I am confused on how to do that. I ...
0
votes
0answers
15 views

What's the input for the cost function?

I'm trying to implement deep Q-learning, but I do not know what to put into the cost function. My net has 8 scalar inputs, 4 scalar outputs (from 0-1) and no hidden layers. To calculate the cost I ...
0
votes
0answers
2 views

Best DDPG use case when having sensor historical data and virtual environment of a real world system

I have a historical data (from real sensors) which have enough knowledge of the actions and states needed for the use of reinforcement learning and a modeled virtual environment of a real system (...
0
votes
0answers
7 views

Learning using DDPG with pyhton solely using historical data

I have a lengthy timeseries datasets which contains several variables (from sensors etc) to be classified as actions or states. Providing they are successfully done, I want to learn a control policy ...
1
vote
1answer
89 views

Evaluating a trained Reinforcement Learning Agent?

I am new to reinforcement learning agent training. I have read about PPO algorithm and used stable baselines library to train an agent using PPO. So my question here is how do I evaluate a trained RL ...
1
vote
0answers
36 views

Transitioning from Math PhD to ML research [closed]

I am currently a Math PhD about to defend in January. I work in a field in functional analysis that uses a lot of measure theory (but no stats). I have been considering transitioning careers since I ...