Stack Overflow
Stack Overflow

Questions tagged [rllib]

Ray RLlib is an open-source Python library for Reinforcement Learning. Use with applicable framework tags, such as TensorFlow or PyTorch.

105 questions
0
votes
0 answers

How can I set or limit the number of cores that a trial is allowed to use?

I am trying to run a trial in RayTune, for which I want to test how the number of cores I throw at the problem affects calculation times. I tried ray.init(num_cpus=foo), but it just utilises all cores on the machine nonetheless, regardless of the…
user18259592
  • 25
  • 3
0
votes
0 answers

GNN/Multi Agent RL in RayRLLib and PyTorch Geometric

Currently trying to add a custom_model on ray rllib, for a GNN using PyTorch. Using multi agent reinforcement learning (Specifically PPO). The scenario is inventory management where I model each node in my supply chain as an agent. I define a…
Niki
  • 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
0 answers

Experience with MARLlib

I trained some MPE environments (simpe_tag,...) in MALlib to see how well it trains.... but I came to a slight problem viewing the results I made and those they uploaded. I am realtivly new to MARL and have no idea if the are good or not. I tried…
Char
  • 1
  • 1
0
votes
0 answers

How to resolve Python Package DeprecationWarning

I received the following error message in Microsoft Visual Studio using the Ray RLlib package in python (Scalable Reinforcement Learning). ray.rllib.agents.callbacks has been deprecated. Use ray.rllib.algorithms.callbacks instead. Are there any…
Michelle
  • 3
  • 2
0
votes
1 answer

Writing a program to train an RL agent in RLlib using a configuration file

I am new to RLlib and trying to write a small program that takes a configuration file and trains an agent. The configuration file is a fine-tuned example for CartPole-v1 environment, and I saved it in cartpole-ppo.yaml. I am aware of RLlib CLI using…
hanugm
  • 1,127
  • 3
  • 13
  • 44
0
votes
0 answers

Error using LSTM model with RLLib for trainning A3C agent

I’m training an A3C agent using RLLib, my observations are 2D (time steps, features), so my first layer should be a LSTM followed by another LSTM and then a fully connected layer before the final layer. I’m using the following config for…
Felipe
  • 1
0
votes
0 answers

RuntimeError: Error(s) in loading state_dict for AuGraphModel_as_DQNTorchModel:

I used Curiosity exploration in rllib, but some errors occurred. Unexpected key(s) in state_dict: "_curiosity_feature_net.post_fc_stack._value_branch._model.0.weight", "_curiosity_feature_net.post_fc_stack._value_branch._model.0.bias",…
pikaz
  • 1
  • 1
0
votes
0 answers

Ray RLlib first example in "Getting Started" page not halting

The Ray RLlib "Getting Started" page says to run the following: pip install "ray[rllib]" tensorflowrllib train --algo DQN --env CartPole-v1 and then says "Running the above will return one of the checkpoints that get generated during training, as…
user118967
  • 4,895
  • 5
  • 33
  • 54
0
votes
1 answer

CMake error in installing Ray on Ubuntu 18.04

I cloned the Ray repository from Github (https://github.com/flow-project/ray.git) and am trying to install it on Ubuntu 18.04. I followed the instructions provided on https://flow.readthedocs.io/en/latest/flow_setup.html, but am encountering an…
FahimSh87
  • 1
  • 1
0
votes
0 answers

RLlib integration with MLflow model registry

I’d like to create a setup in which I can store best checkpoints. It would then serve in two ways: There would be a centralized storage for best checkpoints, with a possibility to specify which model and version use for other trainings…
mlokos
  • 359
  • 2
  • 10
0
votes
1 answer

Is there anyway to do proper action masking while using Ray and an Open Spiel environment?

Whenever I run an Open Spiel environment with Ray, I always get tons of errors about the moves not being legal. I was wondering if there was anyway to apply action masking with an Open Spiel environment. I ran the example included with ray:…
MonisVerse
  • 1
0
votes
1 answer

How do I get value function/critic values from Rllib's PPO algorithm for a range of observations?

Goal: I want to train a PPO agent on a problem and determine its optimal value function for a range of observations. Later I plan to work with this value function (economic inequality research). The problem is sufficiently complex so that dynamic…
Simon
  • 58
  • 5
0
votes
1 answer

OpenAI Gym RLLib AssertionError in CustomEnviorment

I have a custom enviorment: class PlacementEnv(gym.Env) def __init__(self, sb, bb): self.reward = None self.smallBoxes = sb self.bigBoxes = bb # Define the observation space i = 1 …
Jürgen
  • 1
  • 1
0
votes
1 answer

I want to call some layers during training (but not inference) - the gradients don't seem to flow through these layers

I am using a custom PPO model with ray.tune(), and I want to add some self-supervised learning that is dependent on batch[‘obs’], batch[‘done’], batch[‘action’] and batch[‘next_obs’] I have defined some layers in my model that are called only during…
jakethesnack
  • 1
1 2 3 4
5
6 7