Skip to main content
Stack Overflow
  1. About
  3. For Teams
Filter by
Sorted by
Tagged with
1 vote
1 answer
90 views

I tried training a BC algorithm using offline data and enabled the RL module in the algorithm configuration. I ran the code on Google Colab, which only provides 2 CPUs, and encountered the following ...
3 votes
0 answers
69 views

I use ray 2.50.1 to implement a MARL model using PPO. However, I meet the following problem: 'advantages' KeyError: 'advantages' During handling of the above exception, another exception occurred: ...
1 vote
1 answer
138 views

I'm using a slight variant of the RockPaperScissors multi-agent environment from the Ray RLlib documentation as a test environment to verify that a custom RLModule for Centralized Training, ...
0 votes
1 answer
97 views

When I run the following code i get error 'module' object is not callable if __name__ == "__main__": env_name = "4x4grid" register_env( env_name, lambda _: ...
2 votes
1 answer
194 views

I'm training a transformer model using RLlib's PPO algorithm, but I encounter a device mismatch error: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, ...
1 vote
2 answers
318 views

Can anyone explain to me why the episode_reward_mean is NOT part of the results dictionary? Is it replaced by a different key in the latest API? I see env_runners/episode_return_mean and env_runners/...
1 vote
1 answer
80 views

I trained a PPO model with action space self.action_space = gym.spaces.Box(-1, 1, (1,), data_type)" with rllib But when i use the trained model to manually call forward_inference, the inference ...
1 vote
1 answer
69 views

I am quite new to Reinforcement Learning and can’t understand it. I am unable to update configurations for the batch data using PPO. I am using my custom-defined GYM environment, and want to train it ...
2 votes
0 answers
111 views

I'm creating my own gym environment to test the freeze-tag problem. I'm trying to use Ray to do MAPPO. I have two problems: 1: My simulation is not rendering 2: Its creating multiple PyGame windows I'...
0 votes
1 answer
132 views

I'm trying to create a custom MLP-based policy in Ray Rllib using this code below: python: 3.10 Rayrlib version: 2.23 class CustomMLPModel(TorchModelV2, nn.Module): def __init__(self, obs_space, ...
1 vote
0 answers
62 views

I have this very basic custom parallel multi agent environment written in PettingZoo. import functools import random from copy import copy import numpy as np from gymnasium.spaces import Discrete, ...
0 votes
0 answers
30 views

I am having problems initializing the LSTM layers for a PPO+LSTM in RLlib. The inputs expected are different from what I give, and I do not understand why. Here my code: class CustomTorchModel(...
1 vote
0 answers
49 views

im trying to use the AttentionNet GTrXL from RLLIB with a dictionary/tuple gym input. I found this example of complex inputs: Complex input nets. Now im not sure how to combine both properly. I would ...
0 votes
0 answers
326 views

I'm encountering an AttributeError when trying to run a PPO trainer on an OR-GYM environment for inventory management using Ray RLlib and PyTorch in a CPU-only setup. Despite explicitly setting ...
Sumaya's user avatar
  • 1
1 vote
0 answers
51 views

I am using ray rllib to save and load checkpoints. I am using the same version across Mac and Linux. I want to be able train on linux and infer on my Mac but I am getting the following error: ...

15 30 50 per page
1
2 3 4 5
...
8

AltStyle によって変換されたページ (->オリジナル) /