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.
Questions tagged [stable-baselines]
277 questions
0
votes
0 answers
RL agent has troubles understanding game
I was trying to make RL agent which will be able to play board game called hexxagon https://hexxagon.com/.
At the beggining I had problems with actions space because this game is kinda simillar to checkers, you have to chose tile from which you make…
0
votes
0 answers
How to create an observation space for lists of data using stable-baselines3?
I'm working to create an AI player for a simple game. I'm currently using the stable-baselines3 and gym libraries. I'm having a bit of a hard time figuring out how to create an observation space to represent the data about the current game state. As…
pbuchheit
- 1,371
- 1
- 20
- 47
0
votes
0 answers
Can't use tee class output for stable-baselines3 logs
I am trying to train a Stable Baselines agent while generating several logs, both for the console and a log file at the same time. To achieve this, I am using the following code:
os.makedirs(folder_path, exist_ok=True)
file = open(file_path,…
user21848941
0
votes
0 answers
How can i have my Agent only take a Step when he is automatically requested to by my custom gym-environment?
i am trying to implement an reinforcement agent, which decides on choosing machines for orders on a production site. I created a custom env in Simpy which asks the Agent on different times, what machines he wants to choose for specific orders,…
Leo W.
- 1
- 1
0
votes
1 answer
In stable_baselines3 I'm getting an assertion error saying my reset function cannot return a Tuple
I am trying to run the chech_env function in gym (OpenAI version), however it's failing on an assertion error suggesting the environment isn't configured correctly. Specifically it's saying AssertionError: The observation returned by the reset()…
haxonek
- 174
- 1
- 2
- 17
0
votes
0 answers
Alternative to nested tuple/dict for stable baselines observation space
I'm currently in the process of setting up a machine learning project using stable-baselines3 and gym. After setting up a basic skeleton for my environment, I ran the project and got the following error:
File…
pbuchheit
- 1,371
- 1
- 20
- 47
0
votes
0 answers
Execute StableBaselines3 training on GPU
I am trying to train a Stable Baselines 3 PPO Reinforcement Learning Agent using GPU to accelerate the process, but when I run my training, I get this error:
File "/src/train_V1_agents.py", line 67, in
…
user21848941
0
votes
1 answer
State-action transformation of collected experience in stable baselines replay buffer
I am working with stable baselines 3 applied to a very expensive problem. I have set everything up for maximum sample-efficiency already and would like to implement the method described in this article: https://arxiv.org/pdf/2111.03454.pdf Namely,…
Artur
- 407
- 2
- 8
0
votes
0 answers
How to export an A2C model created with stable-baselines3 to PyTorch?
I have trained an A2C model (MlpPolicy) using stable-baselines3 (I am quite new to reinforcement learning and found this to be a good place to start).
However, I now want to use a XRL (eXplainable Reinforcement Learning) method to understand the…
kaiwy
- 1
- 1
0
votes
0 answers
A2C Model not making predictions/not learning after one episode
The model we use is A2C provided by stable_baselines3, in training it works fine and learns over time but in the validation process, no predictions are being made, the model gains no rewards, and the actions are the same throughout. Is there any…
Uzair Gheewala
- 21
- 4
0
votes
0 answers
Can't load custom model in stablebasekines3
I try to load a pretrained model in stablebaselines3, but I get this error instead.
C:\Users\prath\miniconda3\envs\rlunitybutler\lib\site-packages\stable_baselines3\common\save_util.py:166: UserWarning: Could not deserialize object policy_class.…
hogpip
- 1
0
votes
0 answers
Why is my model getting stuck at the PPO('MultiInputPolicy') line when testing my javascript version of JumpKing using stable-baselines3 and PyTorch?
In the code below, I am trying to test my model for a javascript version of JumpKing, and its getting stuck on the line model = PPO("MultiInputPolicy", env, verbose=1)
basically, when I use the debugger and try to step over that line, I get this in…
Wafflol
- 1
- 1
0
votes
0 answers
Can no longer install Stable-baselines after trying to install Atari roms
Yesterday, I installed stable-baselines 3 on Windows 10 by typing the following in the Command Prompt
py -m pip install stable-baselines3[extra]
It installed and I ran it in Python with no issues. Today, I tried downloading some Atari roms to work…
infinitylord
- 175
- 7
0
votes
0 answers
Run stable Baselines agent's learn function storing partial results
I am trying to train a RL agent that needs to carry out quite a heavy process to complete, as it needs to perform certain actions with Selenium webdriver and I do not count with a GPU to speed up this process. Due to this, I have tried several…
user21848941
0
votes
1 answer
Why do I get an AssertionError when trying to load a saved PPO model using stable_baselines3 in Python?
I am taking my first steps in Reinforcement Learning with python and am trying a very basic example, but I am running into a problem I can't find the answer for.
Training and saving the basic PPO model seems to work, but when I try to load the model…
