The missile combat gym simulation environment based on Jsbsim
Todo
# create python env
conda create -n jsbsim python=3.8
# install dependency
pip install torch pymap3d jsbsim geographiclib gym==0.20.0 wandb icecream setproctitle.
- Download Shapely‑1.7.1‑cp38‑cp38‑win_amd64.whl from [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely), and `pip install shaply` from local file.
- Initialize submodules(*JSBSim-Team/jsbsim*): `git submodule init; git submodule update`provide all task configs in envs/JSBSim/configs, each config corresponds to a task.
SingleControl env includes single agent heading task, whose goal is to train agent fly according to the given direction, altitude and velocity. The trained agent can be used to design baselines or become the low level policy of the following combat tasks. We can designed two baselines, as shown in the video:
Todo
Todo
# on linux
cd scripts/sh
bash train_*.sh
# on windows
cd scripts/bat
.\train_*.batWe have provide scripts for linux in scripts/sh and scripts for windows in scripts/bat.
train_heading.shortrain_heading.batis for SingleControl environment heading task.train_vsbaseline.shortrain_vsbaseline.batis for SingleCombat vs-baseline tasks.train_selfplay.shortrain_selfplay.batis for SingleCombat self-play tasks.train_selfplay_shoot.shortrain_selfplay_shoot.batis for SingleCombat self-play shoot missile tasks.train_share_selfplay.shortrain_share_selfplay.batis for MultipleCombat self-play tasks.
It can be adapted to other tasks by modifying a few parameter settings.
--env-nameincludes options ['SingleControl', 'SingleCombat', 'MultipleCombat'].--scenariocorresponds to yaml file inenvs/JBSim/configsone by one.--algorithmincludes options [ppo, mappo], ppo for SingleControl and SingleCombat, mappo for MultipleCombat
The description of parameter setting refers to config.py.
Note that we set parameters --use-selfplay --selfplay-algorithm --n-choose-opponents --use-eval --n-eval-rollout-threads --eval-interval --eval-episodes in selfplay-setting training. --use-prior is only set true for shoot missile tasks.
We use wandb to track the training process. If you set --use-wandb, please replace the --wandb-name with your name.
cd renders
python render*.pyThis will generate a *.acmi file. We can use TacView, a universal flight analysis tool, to open the file and watch the render videos.