Stack Overflow
Stack Overflow

Questions tagged [multi-agent-reinforcement-learning]

Anything related to multi-agent reinforcement learning. Popular frameworks and tools include PettingZoo, RLLib, Melting Pot, Mava, OpenSpiel, Tianshou, PyMARL and more.

Multi-agent reinforcement learning (MARL) is a sub-field of reinforcement learning. It focuses on studying the behavior of multiple agents that coexist in a shared environment. Each agent is motivated by its own rewards, and does actions to advance its own interests; these interests may be opposed to the interests of other agents, resulting in complex group dynamics.

35 questions
4
votes
1 answer

Add a TensorBoard metric from my PettingZoo environment

I'm using Tensorboard to see the progress of the PettingZoo environment that my agents are playing. I can see the reward go up with time, which is good, but I'd like to add other metrics that are specific to my environment. i.e. I'd like TensorBoard…
Ram Rachum
  • 84,019
  • 84
  • 236
  • 374
3
votes
0 answers

RLlib: Multiple training phases with different configurations

I want to do some complicated training using RLlib and I'm not sure how. I have an environment for two agents, and I want to train the first agent while I'm forcing the policy of the second agent to be a hard-coded policy that I write. I want to run…
Ram Rachum
  • 84,019
  • 84
  • 236
  • 374
3
votes
0 answers

RLlib: Using a CNN to train on a 2D grid environment

I’m a newbie to RLlib. I developed a few RLlib environments before and successfully used PPO to train agents on them. Now I developed a 2D grid environment where agents roam around and conquer territory (basically mark some cells as belonging to…
Ram Rachum
  • 84,019
  • 84
  • 236
  • 374
3
votes
1 answer

How can we design rewards for an RL algorithm to incentivize a group metric?

I am using designing a reinforcement learning agent to guide individual cars within a bounded area of roads. The policy determines which route the car should take. Each car can see the cars within 10 miles of it, their velocities, and the road graph…
dangerChihuahua007
  • 20,299
  • 35
  • 117
  • 206
1
vote
0 answers

ValueError: RolloutWorker has no `input_reader` object! Cannot call `sample()` occurs when try to start training in RLlib

I just started to use Ray-RLlib and I try to restructure my VSL algorithm (using SUMO) to be able to work with RLlib. This is a MARL (4 agents) DQN approach. I restructured the environment based on the documentation and created the training…
komate1995
  • 11
  • 2
1
vote
0 answers

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation in PyTorch

I am trying to train an actor-critic network for a multi-agent DDPG network (MADDPG) for 10000 episodes with 25 time steps for each episode. When I start the training, after ten episodes, I get this error for computing the gradients. RuntimeError:…
Enigmacy
  • 53
  • 1
  • 9
1
vote
0 answers

How can I synchronize two Deep Reinforcement Learning agents?

I am doing a project in which I simulate a computer network. Each node of the network is a Deep Reinforcement Learning agent and its states will depend on a global matrix from which they have to take data and then modify data. And that I would like…
Jose Antonio Gomez De La Hiz
  • 58
  • 5
1
vote
1 answer

Specifying observation space for Q-Mix in ray

I see that I have to define players observations for using Qmix + LSTM as here https://github.com/ray-project/ray/issues/8407#issuecomment-627401186 or as in this…
ckorzhik
  • 758
  • 2
  • 7
  • 21
1
vote
2 answers

Multi-agent reinforcement learning versus multi-objective reinforcement learning

everyone. What is the difference between Multi-agent reinforcement learning and Multi-objective reinforcement learning? And can you explain the pros and cons of the two methods? I think both methods can serve some objectives...
youngwoo Oh
  • 33
  • 4
1
vote
2 answers

Problem with PettingZoo and Stable-Baselines3 with a ParallelEnv

I am having trouble in making things work with a Custom ParallelEnv I wrote by using PettingZoo. I am using SuperSuit's ss.pettingzoo_env_to_vec_env_v1(env) as a wrapper to Vectorize the environment and make it work with Stable-Baseline3 and…
Piero Macaluso
  • 1,166
  • 1
  • 10
  • 24
0
votes
0 answers

Using Stable Baselines3 on pettingzoo MPE simple spread

SO I created a stable baseline model using A2C to train simple spread environment from pettingzoo (https://pettingzoo.farama.org/environments/mpe/simple_spread/). I referred to the SB3 tutorial provided at pettingzoo for this, and for some reason I…
ummokay
  • 1
0
votes
0 answers

Pytorch raises RuntimeError: Found dtype Float but expected Double

The said error is raised on learning loop, upon calling loss.backwards function. here's my code: critic_value_ = self.agents[agent].target_critic.forward(states_, …
uri_m
  • 9
  • 3
0
votes
0 answers

ERROR: Could not build wheels for gfootball, which is required to install pyproject.toml-based projects

I am trying to install open-source game "football environment" in a remote cluster which I do not have sudo permission. My steps to install the environment: git clone https://github.com/google-research/football.git cd football/ python3 -m pip…
Dalek
  • 4,168
  • 11
  • 48
  • 100
0
votes
0 answers

Is there a way to make an action space from a context free grammar?

I'm looking to build an agent that can use messages that conform to a context-free grammar as its actions and work in an environment using gymnasium. I see they have a text space, but that doesn't really capture the action space, as messages that…
DataOrc
  • 769
  • 2
  • 8
  • 18
0
votes
0 answers

Technique to identify suppressed customers - Reinforcement learning or Sequential Pattern Mining or Rule Based

If for a particular product customers are recommended each month based on his intent and features. The recommended base is available to us for every month. Lets say a customer doesn't take the product i.e. no conversions. If this happens repeatedly…
Arnav Jain
  • 11
  • 1
1
2 3