Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/door/launch_calql.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python main/offline_to_online_rl/finetune_gym.py \
--agent calql \
--config experiments/configs/train_config.py:adroit_cql \
--project q2rl \
--group door_calql \
--warmup_steps 0 \
--num_offline_steps 20_000 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/door/launch_cql.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python main/offline_to_online_rl/finetune_gym.py \
--agent cql \
--config experiments/configs/train_config.py:adroit_cql \
--project q2rl \
--group door_cql \
--warmup_steps 0 \
--num_offline_steps 20_000 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/door/launch_ibrl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ do
python3 main/ibrl/ibrl_gym.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:adroit_wsrl \
--project q2rl \
--group door_ibrl \
--reward_scale 10.0 \
--reward_bias 5.0 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/door/launch_q2rl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ do
python3 main/q2rl/q2rl_gym.py \
--agent q2rl \
--config experiments/configs/train_config.py:adroit_wsrl \
--project q2rl \
--group door_q2rl \
--reward_scale 10.0 \
--reward_bias 5.0 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/door/launch_wsrl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python3 main/offline_to_online_rl/finetune_gym.py \
--agent sac \
--config experiments/configs/train_config.py:adroit_wsrl \
--project q2rl \
--group door_wsrl \
--num_offline_steps 20_000 \
--resume_path $PROJECT_ROOT/data/policies/rl_offline/door/calql/checkpoint_20000 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/kitchen/launch_ibrl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python3 main/ibrl/ibrl_gym.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:kitchen_wsrl \
--project q2rl \
--group kitchen_ibrl \
--reward_scale 1.0 \
--reward_bias -4.0 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/kitchen/launch_q2rl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python3 main/q2rl/q2rl_gym.py \
--agent q2rl \
--config experiments/configs/train_config.py:kitchen_wsrl \
--project q2rl \
--group kitchen_q2rl \
--reward_scale 1.0 \
--reward_bias -4.0 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/kitchen/launch_wsrl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ do
python3 main/offline_to_online_rl/finetune_gym.py \
--agent sac \
--config experiments/configs/train_config.py:kitchen_wsrl \
--project q2rl \
--group kitchen_wsrl \
--num_offline_steps 250_000 \
--resume_path $PROJECT_ROOT/data/policies/rl_offline/kitchen/calql/checkpoint_250000 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/pen/launch_q2rl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ do
python3 main/q2rl/q2rl_gym.py \
--agent q2rl \
--config experiments/configs/train_config.py:adroit_wsrl \
--project q2rl \
--group pen_q2rl \
--reward_scale 10.0 \
--reward_bias 5.0 \
Expand Down
1 change: 0 additions & 1 deletion experiments/scripts/d4rl/pen/launch_wsrl.sh
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ do
--agent sac \
--group pen_wsrl \
--config experiments/configs/train_config.py:adroit_wsrl \
--project q2rl \
--num_offline_steps 20_000 \
--resume_path $PROJECT_ROOT/data/policies/rl_offline/pen/calql/checkpoint_20000 \
--reward_scale 10.0 \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20 30 40)
for i in {0..1}
for i in {0..4}
do
python3 main/ibrl/ibrl_robosuite_image.py \
--agent=ibrl_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20 30 40)
for i in {0..1}
for i in {0..4}
do
python3 main/ibrl/ibrl_robosuite_image.py \
--agent=ibrl_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ export MUJOCO_GL=egl
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20)
for i in {0..1}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite_image.py \
--agent=q2rl_rs_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ export MUJOCO_GL=egl
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20)
for i in {0..1}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite_image.py \
--agent=q2rl_rs_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20 30 40)
for i in {0..1}
for i in {0..4}
do
python3 main/ibrl/ibrl_robosuite_image.py \
--agent=ibrl_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20 30 40)
for i in {0..1}
for i in {0..4}
do
python3 main/ibrl/ibrl_robosuite_image.py \
--agent=ibrl_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ export MUJOCO_GL=egl
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20)
for i in {0..1}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite_image.py \
--agent=q2rl_rs_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ export MUJOCO_GL=egl
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20)
for i in {0..1}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite_image.py \
--agent=q2rl_rs_image \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ do
python3 main/ibrl/ibrl_robosuite.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:robosuite_ibrl \
--project q2rl \
--group can_state_ibrl_with_data \
--get_demo_buffer=True \
--data_filter_key=train \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@ do
python3 main/ibrl/ibrl_robosuite.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:robosuite_ibrl \
--project q2rl \
--group can_state_ibrl_without_data \
--get_demo_buffer=False \
--reward_scale 5.0 \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ do
python3 main/ibrl/ibrl_robosuite.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:robosuite_ibrl \
--project q2rl \
--group lift_state_ibrl_with_data \
--get_demo_buffer=True \
--data_filter_key=20_percent_train \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,8 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

export DATASET_PATH=$(python -c "from huggingface_hub import snapshot_download; print(snapshot_download('theaiinstitute/q2rl_robomimic_datasets', repo_type='dataset'))")

seed=(0 10 20)
for i in {0..2}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite.py \
--agent=q2rl_rs \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ export MUJOCO_GL=egl
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mujoco210/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia

seed=(0 10 20)
for i in {0..2}
seed=(0 10 20 30 40)
for i in {0..4}
do
python3 main/q2rl/q2rl_robosuite.py \
--agent=q2rl_rs \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ do
python3 main/ibrl/ibrl_robosuite.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:robosuite_ibrl \
--project q2rl \
--group square_state_ibrl_with_data \
--get_demo_buffer=True \
--data_filter_key=train \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@ do
python3 main/ibrl/ibrl_robosuite.py \
--agent ibrl_state \
--config experiments/configs/train_config.py:robosuite_ibrl \
--project q2rl \
--group square_state_ibrl_without_data \
--get_demo_buffer=False \
--reward_scale 5.0 \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ do
python3 main/q2rl/q2rl_robosuite.py \
--agent q2rl_rs \
--config experiments/configs/train_config.py:robosuite_q2rl \
--project q2rl \
--group square_state_q2rl_with_data \
--get_demo_buffer=True \
--demo_path data/datasets/square/ph/low_dim_v141.hdf5 \
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@ do
python3 main/q2rl/q2rl_robosuite.py \
--agent q2rl_rs \
--config experiments/configs/train_config.py:robosuite_q2rl \
--project q2rl \
--group square_state_q2rl_without_data \
--get_demo_buffer=False \
--reward_scale 5.0 \
Expand Down
4 changes: 2 additions & 2 deletions main/ibrl/ibrl_gym.py
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_bool("get_new_rollouts", False, "get new rollouts")
Expand All @@ -100,7 +100,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/ibrl/ibrl_robosuite.py
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_string("demo_path", None, "path to load the demo replay buffer from")
Expand All @@ -113,7 +113,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/ibrl/ibrl_robosuite_image.py
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_string("replay_path", None, "path to load the replay buffer from")
Expand Down Expand Up @@ -106,7 +106,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/offline_to_online_rl/finetune_gym.py
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")

Expand Down Expand Up @@ -124,7 +124,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.exp_name}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/offline_to_online_rl/finetune_robosuite.py
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_bool("get_demo_buffer", False, "Load demo trajs into demo buffer")
Expand Down Expand Up @@ -134,7 +134,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.exp_name}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/offline_to_online_rl/finetune_robosuite_image.py
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_bool("get_demo_buffer", False, "Load demo trajs into demo buffer")
Expand Down Expand Up @@ -136,7 +136,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.exp_name}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/q2rl/q2rl_gym.py
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")

Expand All @@ -98,7 +98,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/q2rl/q2rl_robosuite.py
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_bool("get_new_rollouts", False, "get new rollouts")
Expand Down Expand Up @@ -106,7 +106,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down
4 changes: 2 additions & 2 deletions main/q2rl/q2rl_robosuite_image.py
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@

# wandb
flags.DEFINE_string("exp_name", "", "Experiment name for wandb logging")
flags.DEFINE_string("project", None, "Wandb project folder")
flags.DEFINE_string("project", "q2rl", "Wandb project folder")
flags.DEFINE_string("group", None, "Wandb group of the experiment")
flags.DEFINE_bool("debug", False, "If true, no logging to wandb")
flags.DEFINE_bool("get_new_rollouts", False, "get new rollouts")
Expand Down Expand Up @@ -108,7 +108,7 @@ def main(_):
wandb_config = WandBLogger.get_default_config()
wandb_config.update(
{
"project": "q2rl" or FLAGS.project,
"project": FLAGS.project,
"group": FLAGS.group,
"exp_descriptor": f"{FLAGS.group}_{FLAGS.env}_{FLAGS.agent}_seed{FLAGS.seed}",
}
Expand Down