panda-gym
Set of robotic environments based on PyBullet physics engine and gymnasium. (by qgallouedec)
Gymnasium-Robotics
A collection of robotics simulation environments for reinforcement learning (by Farama-Foundation)
panda-gym | Gymnasium-Robotics | |
---|---|---|
3 | 4 | |
450 | 435 | |
- | 3.9% | |
5.3 | 7.2 | |
5 months ago | 7 days ago | |
Python | Python | |
MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
panda-gym
Posts with mentions or reviews of panda-gym.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-29.
-
Hyperparameters for pick&place with Franka Emika manipulator
I'm trying to solve pick&place (and possibly also the other tasks in this repository) with Franka Emika Panda manipulator implemented in Mujoco. I've tried for long with stable_baseline3 but without any results, someone told me to try with RLLib because has better implementation (?), but still I can't find any solution...
-
SAFE-PANDA-GYM a modification to Panda - Gym to train Safe-RL agents
We develop a modification to the Panda Gym by adding constraints to the environments like Unsafe regions and, constraints on the task. The aim is to develop an environment to test CMDPs (Constraint Markov Decision Process) / Safe-RL algorithms such as CPO, PPO - Lagrangian and algorithms developed by the team. Agents would not only have to come up with optimal policy for control and planning but also ensure they don't violate a constraint.
-
Did anyone try Panda-Gym?
The acquisition of Mujoco makes Openai to remove the robotics from their repo. I had no choice but to find an alternative. Then I found https://github.com/qgallouedec/panda-gym which is built on PyBullet.
Gymnasium-Robotics
Posts with mentions or reviews of Gymnasium-Robotics.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-01-12.
- Gymnasium-Robotics 1.2.0 - which now includes maintained versions of the environments from D4RL and the MaMuJoCo environments - is now live
- Gym-Robotics 1.0 is has been released, and all environments are now updated to use new MuJoCo bindings
-
how to set the distance_threshold value and make it effective
I use the [RL Robotics library](https://github.com/Farama-Foundation/Gym-Robotics) to simulate robots. In the Fetchxxx-Env, the variable distance_threshold is set as 0.05 default to determine whether it completed successfully a task. I try to change it by using
-
Did anyone try Panda-Gym?
Yes, it is a good choice. In case you really like to use the original environments, there is a repo by the Farama Foundation, which moved them to a standalone module: https://github.com/Farama-Foundation/gym-robotics.
What are some alternatives?
When comparing panda-gym and Gymnasium-Robotics you can also consider the following projects:
dm_env - A Python interface for reinforcement learning environments
dreamerv2 - Mastering Atari with Discrete World Models
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
sapai - Super auto pets engine built with reinforment learning training in mind
habitat-api - A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators. [Moved to: https://github.com/facebookresearch/habitat-lab]
dreamer - Dream to Control: Learning Behaviors by Latent Imagination
Safe-panda-gym - OpenaAI Gym Franka Emika Panda robot environment based on PyBullet.