More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt.
A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Python
Category
Model Development
Subcategory
Reinforcement Learning
Keywords
RL
Stars
692
Forks
134
Contributors
1
Created date
2018-01-25
Updated date
2026-10-10
Stars in 1 day
0
Stars in 7 days
1
Rank
14,934
Previous rank
14,764
Rank change
-170
7-day stars rank
10,915
Previous 7-day stars rank
10,973
7-day stars rank change
58
Total stars rank
15,014
Previous total stars rank
14,993
Total stars rank change
-21
Country
UK
README summary
MADDPG-PyTorch PyTorch Implementation of MADDPG from *Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments* (Lowe et. 2017) Requirements OpenAI baselines, commit hash: 98257ef8c9bd23a24a330731ae54ed086d9ce4a7 My fork of Multi-agent Particle Environments PyTorch, version: 0. 0rc3 and Tensorboard-Pytorch, version: 1. 0 (for logging) The versions are just what I used and not necessarily strict requirements. How to Run All training code is contained within . To view options simply run: Results Physical Deception In this task, the two blue agents
are rewarded by minimizing the closest of their distances to the green landmark (only one needs to be close to get optimal reward), while maximizing the distance of the red adversary from the green landmark. The red adversary is rewarded by minimizing it's distance to the green landmark; however, on any given trial, it does not know which landmark is green, so it must follow the blue agents. As such, the blue agents should learn to deceive the red agent
by covering *both* landmarks. Cooperative Communication This task involves two agents, one that is stationary and one that can move. The stationary agent sees the color of the other agent as its observation, and outputs a one-hot communication vector as its action. The moving agent receives the communication vector, as well as its relative distance to all landmarks on the screen; however, it does not know its own color. The goal of both agents is for the moving agent
to reach the landmark that matches its own color. Thus, the agents must learn to communicate such that the moving agent knows where to go on each randomized trial. Predator-Prey This task involves a single prey agent (in green) and a team of three predators (in red). The prey agent is 30% faster than the predators, so the predators must learn how to team up in order to catch the prey. In the trials below, the prey agent uses
DDPG as its learning algorithm. Not Implemented There are a few items from the paper that have not been implemented in this repo Ensemble Training Inferring other agents' policies Mixed continuous/discrete action spaces Acknowledgements The OpenAI baselines Tensorflow implementation and Ilya Kostrikov's Pytorch implementation of DDPG were used as references. After the majority of this codebase was complete, OpenAI released their code for MADDPG, and I made some tweaks to this repo to reflect some of the details in
their implementation (e. gradient norm clipping and policy regularization).
Frequently asked questions
How many stars and forks are recorded?
shariqiqbal2810/maddpg-pytorch has 692 stars and 134 forks.
What is the repository rank?
shariqiqbal2810/maddpg-pytorch is ranked 14,934.
What language and category are recorded?
shariqiqbal2810/maddpg-pytorch has 692 stars, uses Python and belongs to Model Development.
Which repository is closest in rank?
shariqiqbal2810/maddpg-pytorch is compared with tensorflow/decision-forests, ranked 14,935 with 692 stars.
The versions are just what I used and not necessarily strict requirements.
How to Run
All training code is contained within main.py. To view options simply run:
python main.py --help
Results
Physical Deception
In this task, the two blue agents are rewarded by minimizing the closest of their distances to the green landmark (only one needs to be close to get optimal reward), while maximizing the distance of the red adversary from the green landmark. The red adversary is rewarded by minimizing it's distance to the green landmark; however, on any given trial, it does not know which landmark is green, so it must follow the blue agents. As such, the blue agents should learn to deceive the red agent by covering both landmarks.
Cooperative Communication
This task involves two agents, one that is stationary and one that can move. The stationary agent sees the color of the other agent as its observation, and outputs a one-hot communication vector as its action. The moving agent receives the communication vector, as well as its relative distance to all landmarks on the screen; however, it does not know its own color. The goal of both agents is for the moving agent to reach the landmark that matches its own color. Thus, the agents must learn to communicate such that the moving agent knows where to go on each randomized trial.
Predator-Prey
This task involves a single prey agent (in green) and a team of three predators (in red). The prey agent is 30% faster than the predators, so the predators must learn how to team up in order to catch the prey.
In the trials below, the prey agent uses DDPG as its learning algorithm.
Not Implemented
There are a few items from the paper that have not been implemented in this repo
Ensemble Training
Inferring other agents' policies
Mixed continuous/discrete action spaces
Acknowledgements
The OpenAI baselines Tensorflow implementation and Ilya Kostrikov's Pytorch implementation of DDPG were used as references. After the majority of this codebase was complete, OpenAI released their code for MADDPG, and I made some tweaks to this repo to reflect some of the details in their implementation (e.g. gradient norm clipping and policy regularization).
