In this post, we will see how to resolve Why is the mean reward per episode of my PPO and DQN decreasing over time? Question: I am training an RL agent to optimise dispatching in a job shop manufacturing system. ...
In this post, we will see how to resolve ValueError: Layer “model_69” expects 3 input(s), but it received 96 input tensors Question: I am trying not to use model.predict() nor model.fit() in a for loop to speed up training so ...
In this post, we will see how to resolve Can’t set the frame rate when recording a video with VecVideoRecorder Question: I have a working RL model and set up that produce a video for me – however becuase the ...
In this post, we will see how to resolve Best approach to apply RL to pre-built simulator? Question: I’ve built a simulator in python that emulates the process of accepting students into a university. It is fairly complex and I’ve ...
In this post, we will see how to resolve Hyperparameter Tuning with Wandb Sweep for custom parameters Question: I’m trying to tune the hyperparameters using the Stable-Baseline-3 Library for the network architecture. My configuration file is: But if I try ...
In this post, we will see how to resolve Why is my REINFORCE algorithm not learning? Question: I am training a REINFORCE algorithm on the CartPole environment. Due to the simple nature of the environment, I expect it to learn ...
In this post, we will see how to resolve Saving and Loading RL model – DQN algorithm Question: I am training a RL model using the DQN algorithm. At every iteration, I save the model as follows: I want to ...
Question: I am new to the field of Q-learning (QL) and I am trying to implement a small task using QL in MATLAB. The task is : Say there is one transmitter, one receiver and between them there are 10 ...
Question: I am implementing multiple RL agents which share a lot of common attributes and methods but differ in only one. Namely the one that calculates the td_error. Out of the top of my head I can think of 3 ...
Question: I am try to train a DQN model with the following code. The GPU (cuda) usage is always lower than 25 percent. I know the tensorflow backend is consulting the GPU resources, but the usage is low. Is there ...