Replicable-MARL MARLlib issues

Replicable-MARL / MARLlib

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

https://marllib.readthedocs.io

MIT License

887 stars 142 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

When running the iddpg algorithm in the MAMujoco environment, the memory keeps increasing.

#245 whbeats opened 1 week ago
1
Does MARLlib support a mixed scenario where each agent has a different policy?

#244 terranovafr opened 1 week ago
0
Does Marllib support dynamic environments？

#243 libin-star opened 2 weeks ago
0
metadrive agent policy mapping: agent_n more than assigned number of agents

#242 aabdelnaby opened 2 weeks ago
0
Outdated ray requirement (ray=1.8.0)

#241 atstarke opened 1 month ago
1
how to fine tune pre-trained policies for new env ?

#240 SoheilSedghi opened 2 months ago
0
NaN rewards in custom environment

#239 zxnga closed 2 months ago
2
Zero reward in Overcooked environment regardless of algorithm/length of training

#238 promiseve opened 4 months ago
0
[DOC] Fix url

#237 maviva opened 4 months ago
0
Confusing results in simple spread environment

#236 Destiny000621 opened 4 months ago
1
How to set up exploration strategies for Agents?

#235 ChenJiangxi opened 4 months ago
0
Inter-agent communication before compute_actions

#234 bbrighttaer closed 5 months ago
1
Inferencing the learned Policies

#233 arshad171 opened 5 months ago
2
Query Regarding num_workers Setting Resulting in Multiple Concurrent Environments During Training

#232 FanFanFan123456 opened 6 months ago
0
Training agents with IQL

#231 bbrighttaer closed 6 months ago
3
Can the qmix algorithm solve the AirCombat problem and does Marllib support it?

#230 Marioooooooooooooo opened 6 months ago
0
IQL setup for Custom Env

#229 thomasychen opened 6 months ago
0
How do I get an agent's position in the environment in the `postprocess_trajectory` method?

#228 bbrighttaer closed 5 months ago
1
How to export trained model as a .pt (pytorch ) or ONNX model.

#227 manaspalaparthi opened 7 months ago
2
Supporting Individual Action Spaces

#226 arshad171 opened 7 months ago
0
Episodes_this_iter parameter

#225 Nafisanaznin opened 7 months ago
0
Trouble implementing custom environment

#224 allenjeffreywu opened 7 months ago
3
JointQ not work in custom env

#223 Yilgrimage opened 7 months ago
1
Doing Counterfactual Experience Replay

#222 nikhil-pitta opened 7 months ago
9
Update to newest RLlib version?

#221 ardian-selmonaj opened 7 months ago
5
How MARLlib works with ray algorithms like PPO?

#220 SaraRezaei closed 7 months ago
1
"MulBackward0 returned nan values" error when launch HATRPO after HAPPO

#219 TheShenk opened 7 months ago
0
How ma_policy works? and How I can use it?

#218 SaraRezaei opened 8 months ago
0
Discrete action space switching continuous action space problem in custom environment

#217 shengqie opened 8 months ago
1
Access Value Function After algo.Fit

#216 thomasychen closed 7 months ago
2
reslink in model

#215 fulacse opened 8 months ago
0
The problems about Modify the network structure.

#214 libin-star opened 8 months ago
4
Backpropagation through time for PPO

#213 fulacse opened 9 months ago
1
Can not save video

#212 fulacse closed 8 months ago
3
Where is numpy.object_ from?

#211 fulacse closed 9 months ago
3
Continue my Training process

#210 DuangZhu closed 8 months ago
1
Evaluating agents after training

#209 Nafisanaznin closed 8 months ago
2
AttributeError: 'MAPPOTrainer' object has no attribute '_local_ip'

#208 gyccccccccc closed 9 months ago
3
Help with questions about custom environments

#207 huigeopencv opened 9 months ago
3
Working with my own customized env

#206 HawkQ opened 9 months ago
3
TypeError in ray

#205 ErwinLiYH closed 8 months ago
3
cannot train ma-gym environment with IQL

#204 Nafisanaznin opened 10 months ago
6
Marllib seems never uses gpu devices

#203 wmzfight opened 10 months ago
4
trainning stopped because of OOM

#202 Rocinate opened 10 months ago
3
Configuration of custom environment

#201 BonnenuIt opened 10 months ago
2
There is a bug in def central_value_function(self, state, opponent_actions=None) in cc_mlp.py and needs to be modified.

#200 Maxwell-R opened 10 months ago
1
AircraftSimulator use of bloods?

#199 ardian-selmonaj opened 10 months ago
0
Does this framework support asynchronous execution of the step function for different agents?

#198 JSA-458 closed 10 months ago
1
Unable to install globally using setup.py

#197 AlbertoSinigaglia closed 10 months ago
1
Any roadmap?

#196 Rocinate closed 10 months ago
1