[Docs] Add more baselines for PPO

haosulab · Feb 3, 2025 · 1055873 · 1055873
1 parent c7665f2
commit 1055873
Show file tree

Hide file tree

Showing 2 changed files with 26 additions and 6 deletions.
diff --git a/examples/baselines/act/baselines.sh b/examples/baselines/act/baselines.sh
@@ -42,21 +42,21 @@ done
 for demos in 100; do
   python train_rgbd.py --env-id PickCube-v1 --no_include_depth \
     --demo-path ~/.maniskill/demos/PickCube-v1/motionplanning/trajectory.rgb.pd_ee_delta_pos.physx_cpu.h5 \
-    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cpu" --num_demos $demos --max_episode_steps 100 \
+    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cuda" --num_demos $demos --max_episode_steps 100 --num_eval_envs 100 --no-capture-video \
     --total_iters 30000 --log_freq 100 --eval_freq 5000 \
     --exp-name=act-PickCube-v1-state-${demos}_motionplanning_demos-$seed \
     --demo_type motionplanning --track --wandb_entity "stonet2000"
 
   python train_rgbd.py --env-id PushCube-v1 --no_include_depth \
     --demo-path ~/.maniskill/demos/PushCube-v1/motionplanning/trajectory.rgb.pd_ee_delta_pos.physx_cpu.h5 \
-    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cpu" --num_demos $demos --max_episode_steps 100 \
+    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cuda" --num_demos $demos --max_episode_steps 100 --num_eval_envs 100 --no-capture-video \
     --total_iters 30000 --log_freq 100 --eval_freq 5000 \
     --exp-name=act-PushCube-v1-state-${demos}_motionplanning_demos-$seed \
     --demo_type motionplanning --track --wandb_entity "stonet2000"
 
   python train_rgbd.py --env-id StackCube-v1 --no_include_depth \
     --demo-path ~/.maniskill/demos/StackCube-v1/motionplanning/trajectory.rgb.pd_ee_delta_pos.physx_cpu.h5 \
-    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cpu" --num_demos $demos --max_episode_steps 200 \
+    --control-mode "pd_ee_delta_pos" --sim-backend "physx_cuda" --num_demos $demos --max_episode_steps 200 --num_eval_envs 100 --no-capture-video \
     --total_iters 30000 --log_freq 100 --eval_freq 5000 \
     --exp-name=act-StackCube-v1-state-${demos}_motionplanning_demos-$seed \
     --demo_type motionplanning --track --wandb_entity "stonet2000"

diff --git a/examples/baselines/ppo/baselines.sh b/examples/baselines/ppo/baselines.sh
@@ -96,8 +96,8 @@ done
 for seed in ${seeds[@]}
 do
   python ppo_fast.py --env_id="PegInsertionSide-v1" --seed=${seed} \
-    --num_envs=1024 --update_epochs=8 --num_minibatches=32 --gamma=0.97 --gae_lambda=0.95 \
-    --total_timesteps=150_000_000 --num-steps=100 --num-eval-steps=100 \
+    --num_envs=2048 --update_epochs=8 --num_minibatches=32 --gamma=0.97 --gae_lambda=0.95 \
+    --total_timesteps=75_000_000 --num-steps=16 --num-eval-steps=100 \
     --num_eval_envs=16 \
     --save-model --cudagraphs --exp-name="ppo-PegInsertionSide-v1-state-${seed}-walltime_efficient" \
     --wandb_entity="stonet2000" --track
@@ -133,6 +133,16 @@ do
     --wandb_entity="stonet2000" --track
 done
 
+for seed in ${seeds[@]}
+do 
+  python ppo_fast.py --env_id="OpenCabinetDrawer-v1" --seed=${seed} \
+    --num_envs=1024 --update_epochs=8 --num_minibatches=32 \
+    --total_timesteps=50_000_000 --num-steps=16 --num-eval-steps=100 \
+    --num_eval_envs=16 \
+    --save-model --cudagraphs --exp-name="ppo-OpenCabinetDrawer-v1-state-${seed}-walltime_efficient" \
+    --wandb_entity="stonet2000" --track
+done
+
 ### RGB Based PPO Baselines ###
 for seed in ${seeds[@]}
 do
@@ -162,4 +172,14 @@ do
     --num_eval_envs=16 \
     --exp-name="ppo-PushT-v1-rgb-${seed}-walltime_efficient" \
     --wandb_entity="stonet2000" --track
-  done
+done
+
+for seed in ${seeds[@]}
+do 
+  python ppo_rgb.py --env_id="AnymalC-Reach-v1" --seed=${seed} \
+    --num_envs=1024 --update_epochs=8 --num_minibatches=32 --gamma=0.99 --gae_lambda=0.95 \
+    --total_timesteps=50_000_000 --num-steps=16 --num-eval-steps=200 \
+    --num_eval_envs=16 --eval-reconfiguration-freq=0 \
+    --exp-name="ppo-AnymalC-Reach-v1-rgb-${seed}-walltime_efficient" \
+    --wandb_entity="stonet2000" --track
+done