https://github.com/coac/commnet-bicnet
CommNet and BiCnet implementation in tensorflow
https://github.com/coac/commnet-bicnet
multi-agent-reinforcement-learning reinforcement-learning tensorflow
Last synced: 11 months ago
JSON representation
CommNet and BiCnet implementation in tensorflow
- Host: GitHub
- URL: https://github.com/coac/commnet-bicnet
- Owner: Coac
- Created: 2018-05-19T11:56:32.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-07-27T11:13:25.000Z (almost 8 years ago)
- Last Synced: 2023-10-25T21:28:52.721Z (over 2 years ago)
- Topics: multi-agent-reinforcement-learning, reinforcement-learning, tensorflow
- Language: Python
- Size: 66.4 KB
- Stars: 53
- Watchers: 4
- Forks: 17
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CommNet-BiCnet
[CommNet](https://arxiv.org/abs/1605.07736) and [BiCnet](https://arxiv.org/abs/1703.10069) implementation in tensorflow
## Training
Train CommNet using DDPG algorithm
```
python train_comm_net.py
```
## Hypersearch
To find the optimal hyperparameters such as `actor_lr` or `critic_lr`, a simple grid search has been implemented. It launches multiple instances of the trainer in parallel based on the number of CPU cores.
```
python hypersearch.py
```
## Guessing sum environment
It is a simple game described in the [BiCnet](https://arxiv.org/abs/1703.10069) paper for testing if the communication works. The environment implements the crucial methods of the core gym interface from OpenAI
Each agent receives a scalar sampled between `[−10, 10]` under a truncated Gaussian. Each agent needs to output the sum of all inputs received among the agents. An agent gets a normalized reward between `[0, 1]` based on the absolute difference between the sum and its output.
## Results
### Training CommNet in the Guessing sum env with 2 agents
