conda create -n swarm-rl python=3.8
conda activate swarm-rl

git clone https://github.com/alex-petrenko/quad-swarm-rl
cd quad-swarm-rl
pip install -e .

python -m swarm_rl.train --env=quadrotor_multi --train_for_env_steps=1000000000 --algo=APPO \
--use_rnn=False \
--num_workers=36 --num_envs_per_worker=4 \
--learning_rate=0.0001 --ppo_clip_value=5.0 \
--recurrence=1 --nonlinearity=tanh --actor_critic_share_weights=False \
--policy_initialization=xavier_uniform --adaptive_stddev=False --with_vtrace=False \
--max_policy_lag=100000000 --hidden_size=256 --gae_lambda=1.00 --max_grad_norm=5.0 \
--exploration_loss_coeff=0.0 --rollout=128 --batch_size=1024 --quads_use_numba=True \
--quads_mode=mix --quads_episode_duration=15.0 --quads_formation_size=0.0 \
--encoder_custom=quad_multi_encoder --with_pbt=False --quads_collision_reward=5.0 \
--quads_neighbor_hidden_size=256 --neighbor_obs_type=pos_vel --quads_settle_reward=0.0 \
--quads_collision_hitbox_radius=2.0 --quads_collision_falloff_radius=4.0 --quads_local_obs=6 \
--quads_local_metric=dist --quads_local_coeff=1.0 --quads_num_agents=8 --quads_collision_reward=5.0 \
--quads_collision_smooth_max_penalty=10.0 --quads_neighbor_encoder_type=attention \
--replay_buffer_sample_prob=0.75 --anneal_collision_steps=300000000 --experiment=swarm_rl 

python -m sample_factory.runner.run --run=swarm_rl.runs.quad_multi_mix_baseline_attn --runner=processes --max_parallel=4 --pause_between=1 --experiments_per_gpu=1 --num_gpus=4

tensorboard --logdir=./

python -m swarm_rl.enjoy --algo=APPO --env=quadrotor_multi --replay_buffer_sample_prob=0 --continuous_actions_sample=False --quads_use_numba=False --train_dir=PATH_TO_PROJECT/swarm_rl/train_dir --experiments_root=EXPERIMENT_ROOT --experiment=EXPERIMENT_NAME

./run_tests.sh