gym-pybullet-drones
HighwayEnv
gym-pybullet-drones | HighwayEnv | |
---|---|---|
4 | 3 | |
1,089 | 2,361 | |
2.8% | 1.9% | |
8.4 | 7.5 | |
10 days ago | 7 days ago | |
Python | Python | |
MIT License | MIT License |
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.
gym-pybullet-drones
-
Drone Racing RL Environments
Gym-pybullet-drones (https://github.com/utiasDSL/gym-pybullet-drones)
-
drone environment ?
https://github.com/utiasDSL/gym-pybullet-drones I have used this library and liked it a lot. It comes with a ready quadcopter and environment. I think at the initialization step you should be able to apply random force for throwing effect.
- How to simulate solidworks model with python?
- Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control
HighwayEnv
-
Looking for a a tutorial/blog post/ codebase/ anything that deals with highway-env possibly the racetrack variant) with a DQN
More or less what the title says. I have already tried this https://github.com/Farama-Foundation/HighwayEnv/blob/master/scripts/sb3_racetracks_ppo.py, using a dqn from sb3 instead of the ppo but the results weren't good, i'm open to any suggestion.
-
RecurrentPPO (SB3-contrib) learning for autonomous driving
Hi everyone! I'm a complete newbie to DRL, so please forgive my lack of understanding of some things on here. I'm training a recPPO from SB3-contrib on E.Leurent's Highway env [https://github.com/eleurent/highway-env] (I customized the action to be more high-level). During training I get the desired behavioural outcome from the agent but I noticed that some training metrics of the model seem quite off respect to the trend found online (especially the explained variance). I just wanted an opinion from some more navigated fellas in here! Can I somehow fix this trend by hyperparameter tuning or do I have e.g. to modify the reward function somehow? How can I improve the training? For any details I'm always available. I share the tensorboard plots obtained for RecPPO.
-
Low Graphics Consuming Simulators for Self-Driving Cars
This is an excellent one https://github.com/eleurent/highway-env
What are some alternatives?
robot-gym - RL applied to robotics.
deepdrive-zero - Top down 2D self-driving car simulator built for running experiments in minutes, not weeks
pybullet-gym - Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
MuJoCo_RL_UR5 - 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.
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
gym-md - MiniDungeons for OpenAI Gym
Bullet - Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
PythonRobotics - Python sample codes for robotics algorithms.
on-policy - This is the official implementation of Multi-Agent PPO (MAPPO).
rocket-league-gym - A Gym-like environment for Reinforcement Learning in Rocket League
isaac_ros_apriltag - Hardware-accelerated Apriltag detection and pose estimation.
multirotor - Multicopter UAV simulation for control/RL experiments.