Stack Overflow
Stack Overflow

Questions tagged [stable-baselines]

Stable Baselines is a library with implementations of various reinforcement learning algorithms in Python, developed by OpenAI. Please mention the exact version of Stable Baselines that is being used in the body of the question.

277 questions
0
votes
1 answer

stable_baselines3 PPO model crashes during training due to error in dummy_vec_env.py

I am attempting to train a PPO model on the CartPole-v1 environment. import gym from stable_baselines3 import PPO from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize from stable_baselines3.common.env_util import make_vec_env from…
Ethan C
  • 1
  • 3
0
votes
0 answers

basic confusion about vector environment combined with stable baseline model predict

I’d like to make my basic confusion clear by some demo codes below. So as usual, when we need to train multiply we use SubprocVecEnv to define env. but when it comes to load saved model and making the test run, we should still pass a SubprocVecEnv…
pborz
  • 1
  • 1
0
votes
0 answers

My stable-baselines3 script is interrupted in singularity images and no logs

I try to train a custom environment by stable-baselines3 inside a singularity images.But it is always interrupted by SIGTEM.Here are the informations: Loguru caught a signal: SIGTERM Loguru caught a signal: SIGTERM Loguru caught a signal:…
Leestring
  • 1
0
votes
1 answer

Getting Environment must inherit from the gym.Env when it already does in Stable Baselines3

I have a script where I try to use stable_baselines3.__version__='2.0.0a5' methods over a custom Gym environment. The thing is that, even if my environment does inherit from the gym.Env class, I get the error AssertionError: Your environment must…
user21848941
0
votes
0 answers

Vizdoom and gymnasium multiple enviroments

I'm using gymnasium with Vizdoom, trying to apply the A2C algorithm with stable baselines. I know gymnasium supports multiple enviroments (Example here) but I was wondering if it's possible to do with a third party enviroment. If it's possible,…
Joaquin
  • 139
  • 1
  • 3
  • 12
0
votes
0 answers

2D Binpacking using RL

I am working on a project that involves solving a 2D bin packing problem using reinforcement learning (RL). I am facing a challenge with training the RL. It seems that the RL does not learn to improve its performance over time, and it often produces…
Philipp Gradl
  • 1
  • 1
0
votes
0 answers

Can the actor policy *function* be used to update the state in Gymnasium/PettingZoo?

I am trying to transition from hard-coding RL algorithms myself to using libraries like Stable Baselines 3 and RL-Lib, with environments built using Farama Foundation's Gymnasium and Petting Zoo libraries. However, many of the environments I am…
42bsk
  • 76
  • 1
  • 10
0
votes
1 answer

Hyperparameter tuning for Custom Gym Env in Stable Baselines3 using RL Zoo

I have created a Gym environment and am able to train it via PPO from Stable Baselines3. However, I am not getting desired results. The agent seems to be stuck at the local optimum rather than the global one. However, even reaching this stage…
Manish
  • 458
  • 6
  • 19
0
votes
1 answer

No module named 'stable_baselines3.evaluation'

I am have trying to learn more about reinforcement learning algorithms, whilst applying them at the same time. I am following steps to build my environment and model using this link https://blog.paperspace.com/projects-with-reinforcement-learning/ .…
Aayush Jain
  • 1
  • 1
0
votes
0 answers

A question about configuring stablelines3 on ubuntu18.04

I have a question about stablebaselines3 configuration on ubuntu18.04. First I created a python3.7 virtual environment, then I downloaded gym0.26.2, successfully installed; then I used pip install stable-baselines3[extra], but there was a…
不摇碧莲
  • 1
  • 1
0
votes
0 answers

Writing callback when explained variance is within a range

I am currently writing a reinforcement learning model using stable_baselines3 library and gym_anytrading. I have written the code for an environment to train the model in and have a number of timesteps. However, the model often finishes its training…
ET4
  • 1
0
votes
0 answers

Custom Policy stable-baselines3

I'm trying to create a custom Policy for A2C with stable-baselines3, but I'm stuck. I'm using a MultiBinary observation space (80x80 grid) and continuous actions. self.action_space = Box( low=-1.0, high=1.0, shape=(4,),…
Claudiu Filip
  • 19
  • 4
0
votes
0 answers

How to stop the learning process with PPO in stablelines?

So, I created a custom environment based on gymnasium and I want to train it with PPO from stable_baselines3. I'm using version 2.0.0a5 of the latter, in order to use gymnasium. I have the following code: env = MyEnv() model = PPO("MlpPolicy", env,…
Benares
  • 1,186
  • 1
  • 7
  • 13
0
votes
0 answers

parallel evaluation by multiprocessing not possible for stable_baselines3?

I know that stable_baselines3 is able to train in parallel with make_vec_env. However, I can't find any info whether evaluation is parallelizable. So I tried to do it on customized env which has ids indicating different episodes because I'd like the…
zhh210
  • 388
  • 4
  • 12
0
votes
0 answers

Open AI gym custom gym environment training PPO stable baseline3

I have made a custom gym environment where the goal of the agent is to maintain around the target state that I specified. I have designed my reward system so that if it is in a specific range give specific rewards for it. However, my agent seems…
johndiggle840
  • 1
  • 1
1 2 3
…
18 19