Skip to main content

Questions tagged [stable-baselines]

For questions that involve the stable-baseline libraries for reinforcement learning. However, note that programming questions are off-topic here. You should use this tag only to contextualize your problem and solution.

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

Parametric noise over Input noise

I came across this research from 2017 that talked about using "Parametric noise" instead of input based noise. I have tried to have it in my PPO based Boid flocking custom environment but ...
Hamza's user avatar
  • 1
0 votes
1 answer
80 views

Why is PPO not choosing a solution that is giving a higher cumulative reward?

I use PPO to train my fermenter (digital twin) to maximize enzyme (product) production. action: 1 or 0 ie. add substrate at a particular time or not based on cell and enzymes present in the tank ...
user79474's user avatar
0 votes
0 answers
25 views

Need help figuring out how I should design my reinforcement learning environment

So I recently had a dumb idea to basically use RL for procedural generation. I want to start with terrain generation, but as a newcomer to RL and someone who can't quite put into words what makes a ...
ChrisNonyminus's user avatar
2 votes
0 answers
51 views

How does PPO with advantage normalization learn in MountainCar-v0 before first reaching the goal state?

I'm trying to figure out how PPO ever learns anything in a sparse environment like gymnasium's MountainCar-v0 before it first ever reaches the goal state. Specifically was looking at stable_baselines3'...
Switch's user avatar
  • 121
0 votes
2 answers
337 views

I'm trying to understand the use model for different Python libraries

I'm new to ML/AI field, and after completing several free university courses from MIT OpenCourseWare and Harvard CS50, I've gained some familiarity with the theoretical foundations of Artificial ...
Boris L.'s user avatar
  • 109
4 votes
1 answer
184 views

Training an RL model with an environment where some of the variables do not change as a result of the agent actions

Typically training an RL model requires an action and an observation space, and the agent learns how its actions affect the observations. Even though there are cases where the observation space ...
Jesuspc's user avatar
  • 151
0 votes
0 answers
46 views

Using deep reinforcement learning for malware detection; trained agent mostly performs the same action

I'm trying to implement this article: Ransomware early detection using deep reinforcement learning on portable executable header The article uses an unpublished dataset of benign and ransomware ...
soosan123's user avatar
1 vote
1 answer
300 views

Getting always the same action on an A2C from stable_baselines3

I'm quite new to RL and have been trying to train an A2C model from stable_baselines3 to derive an integer sequence based on 3 other input sequences of floats. I have a custom gym environment that ...
Jesuspc's user avatar
  • 151
0 votes
2 answers
146 views

Reinforcement learning: Find the fastest solution (minimal number of steps)

I have a Gym env (env) for which I train with a model using the PPO algorithm with stable-baselines. ...
P. Egli's user avatar
  • 101
0 votes
1 answer
66 views

How to expand an agent's action space with more actions?

I'm training a FPS agent using StableBaselines 3's PPO algorithm. To aid learning, I would like to train the agent using just a basic set of actions (e.g Turn left, turn right, shoot). After the agent ...
Ilija Vuk's user avatar
  • 103
5 votes
1 answer
565 views

Why is it recommended to use a "separate test environment" when evaluating a model?

I am training an agent (stable baselines3 algorithm) on a custom environment. During training, I want to have a callback so that for every $N$ steps of the learning process, I get the current model ...
jgklsdjfgkldsfaSDF's user avatar
1 vote
0 answers
245 views

How to normalize input data to Reinforcement learning platform (Gym and stable-baselines)

I created a custom environment with Gym and trained it with stable baseline 3 algorithms. The observation and space action are both continues. The observation space includes 10 values and action space ...
Soprano's user avatar
  • 11
2 votes
0 answers
231 views

Compare Stable-Baselines3 vs. Tianshou [closed]

What would you recommend between Stable-Baselines3 and Tianshou for applied research in Reinforcement Learning? Can anyone provide a comparison of the strengths and weaknesses of each library? Or at ...
SuperTardigrade's user avatar
0 votes
0 answers
714 views

RL-based trading bot: how to deal with overfitting

I've been playing around building a reinforcement learned-based trading bot using the stable-baselines3 library. I've come up with an environment that seems to be able to learn how to make profitable ...
dubvice's user avatar
  • 101
3 votes
0 answers
236 views

How to deal with variable action ranges in RL for continuous action spaces

I am reading this paper on battery management using RL. The action consist in the charging/discharging power of the battery at timestep $t$. For instance, in the case of the charging power, the ...
Leibniz's user avatar
  • 69
2 votes
2 answers
483 views

A2C: Why do episode rewards reset?

I am training a model using A2C with stable baselines 2. When I increased the timesteps I noticed that episode rewards seem to reset (see attached plot). I don´t understand where these sudden decays ...
qwertz's user avatar
  • 21
1 vote
0 answers
487 views

What method is better to use for a two-player reinforcement learning environment?

I want to create an RL agent for a mancala-type two-player game as my first actual project in the field. I've already completed the game itself and coded a minimax algorithm. The question is: how ...
JollyOwl's user avatar