chore: move system config files into separate folders (#119)

EdanToledo · Sep 20, 2024 · b744c8b · b744c8b
1 parent e10dc3e
commit b744c8b
Show file tree

Hide file tree

Showing 52 changed files with 33 additions and 28 deletions.
diff --git a/bash_scripts/run-algorithms.sh b/bash_scripts/run-algorithms.sh
@@ -18,8 +18,13 @@ python stoix/systems/ddpg/ff_td3.py arch.total_timesteps=300 arch.total_num_envs
 python stoix/systems/vpg/ff_reinforce.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
 python stoix/systems/awr/ff_awr.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
 python stoix/systems/mpo/ff_mpo.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
+python stoix/systems/mpo/ff_vmpo.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
+python stoix/systems/search/ff_az.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
+python stoix/systems/search/ff_mz.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8
 
 # Test a subset of networks
 python stoix/systems/ppo/anakin/ff_ppo.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8 env=gymnax/breakout env.wrapper=null network=cnn network.actor_network.pre_torso.channel_first=False network.critic_network.pre_torso.channel_first=False
 python stoix/systems/ppo/anakin/ff_ppo.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8 env=gymnax/breakout env.wrapper=null network=visual_resnet network.actor_network.pre_torso.channel_first=False network.critic_network.pre_torso.channel_first=False
 python stoix/systems/ppo/anakin/ff_ppo.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8 network=mlp_resnet
+python stoix/systems/q_learning/ff_dqn.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8 network=mlp_dueling_dqn
+python stoix/systems/q_learning/ff_c51.py arch.total_timesteps=300 arch.total_num_envs=8 arch.num_evaluation=1 system.rollout_length=8 network=mlp_dueling_c51
diff --git a/stoix/configs/default/anakin/default_ff_awr.yaml b/stoix/configs/default/anakin/default_ff_awr.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_awr
+  - system: awr/ff_awr
   - network: mlp
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_awr_continuous.yaml b/stoix/configs/default/anakin/default_ff_awr_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_awr
+  - system: awr/ff_awr
   - network: mlp_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_az.yaml b/stoix/configs/default/anakin/default_ff_az.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_az
+  - system: search/ff_az
   - network: mlp
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_c51.yaml b/stoix/configs/default/anakin/default_ff_c51.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_c51
+  - system: q_learning/ff_c51
   - network: mlp_c51
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_d4pg.yaml b/stoix/configs/default/anakin/default_ff_d4pg.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_d4pg
+  - system: ddpg/ff_d4pg
   - network: mlp_d4pg
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_ddpg.yaml b/stoix/configs/default/anakin/default_ff_ddpg.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_ddpg
+  - system: ddpg/ff_ddpg
   - network: mlp_ddpg
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_ddqn.yaml b/stoix/configs/default/anakin/default_ff_ddqn.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_dqn
+  - system: q_learning/ff_dqn
   - network: mlp_dqn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_dpo_continuous.yaml b/stoix/configs/default/anakin/default_ff_dpo_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_dpo
+  - system: ppo/ff_dpo
   - network: mlp_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_dqn.yaml b/stoix/configs/default/anakin/default_ff_dqn.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_dqn
+  - system: q_learning/ff_dqn
   - network: mlp_dqn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_dqn_reg.yaml b/stoix/configs/default/anakin/default_ff_dqn_reg.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_dqn_reg
+  - system: q_learning/ff_dqn_reg
   - network: mlp_dqn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_mdqn.yaml b/stoix/configs/default/anakin/default_ff_mdqn.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_mdqn
+  - system: q_learning/ff_mdqn
   - network: mlp_dqn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_mpo.yaml b/stoix/configs/default/anakin/default_ff_mpo.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_mpo
+  - system: mpo/ff_mpo
   - network: mlp_mpo
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_mpo_continuous.yaml b/stoix/configs/default/anakin/default_ff_mpo_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_mpo_continuous
+  - system: mpo/ff_mpo_continuous
   - network: mlp_mpo_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_mz.yaml b/stoix/configs/default/anakin/default_ff_mz.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_mz
+  - system: search/ff_mz
   - network: muzero
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_ppo.yaml b/stoix/configs/default/anakin/default_ff_ppo.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_ppo
+  - system: ppo/ff_ppo
   - network: mlp
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_ppo_continuous.yaml b/stoix/configs/default/anakin/default_ff_ppo_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_ppo
+  - system: ppo/ff_ppo
   - network: mlp_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_qr_dqn.yaml b/stoix/configs/default/anakin/default_ff_qr_dqn.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_qr_dqn
+  - system: q_learning/ff_qr_dqn
   - network: mlp_qr_dqn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_rainbow.yaml b/stoix/configs/default/anakin/default_ff_rainbow.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_rainbow
+  - system: q_learning/ff_rainbow
   - network: mlp_noisy_dueling_c51
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_reinforce.yaml b/stoix/configs/default/anakin/default_ff_reinforce.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_reinforce
+  - system: vpg/ff_reinforce
   - network: mlp
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_reinforce_continuous.yaml b/stoix/configs/default/anakin/default_ff_reinforce_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_reinforce
+  - system: vpg/ff_reinforce
   - network: mlp_continuous
   - env: gymnax/pendulum
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_sac.yaml b/stoix/configs/default/anakin/default_ff_sac.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_sac
+  - system: sac/ff_sac
   - network: mlp_sac
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_sampled_az.yaml b/stoix/configs/default/anakin/default_ff_sampled_az.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_sampled_az
+  - system: search/ff_sampled_az
   - network: mlp_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_sampled_mz.yaml b/stoix/configs/default/anakin/default_ff_sampled_mz.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_sampled_mz
+  - system: search/ff_sampled_mz
   - network: sampled_muzero
   - env: gymnax/pendulum
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_td3.yaml b/stoix/configs/default/anakin/default_ff_td3.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_td3
+  - system: ddpg/ff_td3
   - network: mlp_ddpg
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_vmpo.yaml b/stoix/configs/default/anakin/default_ff_vmpo.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_vmpo
+  - system: mpo/ff_vmpo
   - network: mlp
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/default_ff_vmpo_continuous.yaml b/stoix/configs/default/anakin/default_ff_vmpo_continuous.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_vmpo_continuous
+  - system: mpo/ff_vmpo_continuous
   - network: mlp_continuous
   - env: brax/ant
   - _self_

diff --git a/stoix/configs/default/anakin/default_rec_ppo.yaml b/stoix/configs/default/anakin/default_rec_ppo.yaml
@@ -1,7 +1,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: rec_ppo
+  - system: ppo/rec_ppo
   - network: rnn
   - env: gymnax/cartpole
   - _self_

diff --git a/stoix/configs/default/anakin/hyperparameter_sweep.yaml b/stoix/configs/default/anakin/hyperparameter_sweep.yaml
@@ -3,7 +3,7 @@
 defaults:
   - logger: base_logger
   - arch: anakin
-  - system: ff_ppo
+  - system: ppo/ff_ppo
   - network: mlp
   - env: gymnax/cartpole
   - override hydra/sweeper: optuna

diff --git a/stoix/configs/system/ff_awr.yaml → stoix/configs/system/awr/ff_awr.yaml b/stoix/configs/system/ff_awr.yaml → stoix/configs/system/awr/ff_awr.yaml
diff --git a/stoix/configs/system/ff_d4pg.yaml → stoix/configs/system/ddpg/ff_d4pg.yaml b/stoix/configs/system/ff_d4pg.yaml → stoix/configs/system/ddpg/ff_d4pg.yaml
diff --git a/stoix/configs/system/ff_ddpg.yaml → stoix/configs/system/ddpg/ff_ddpg.yaml b/stoix/configs/system/ff_ddpg.yaml → stoix/configs/system/ddpg/ff_ddpg.yaml
diff --git a/stoix/configs/system/ff_td3.yaml → stoix/configs/system/ddpg/ff_td3.yaml b/stoix/configs/system/ff_td3.yaml → stoix/configs/system/ddpg/ff_td3.yaml
diff --git a/stoix/configs/system/ff_mpo.yaml → stoix/configs/system/mpo/ff_mpo.yaml b/stoix/configs/system/ff_mpo.yaml → stoix/configs/system/mpo/ff_mpo.yaml
diff --git a/stoix/configs/system/ff_mpo_continuous.yaml → ...configs/system/mpo/ff_mpo_continuous.yaml b/stoix/configs/system/ff_mpo_continuous.yaml → ...configs/system/mpo/ff_mpo_continuous.yaml
diff --git a/stoix/configs/system/ff_vmpo.yaml → stoix/configs/system/mpo/ff_vmpo.yaml b/stoix/configs/system/ff_vmpo.yaml → stoix/configs/system/mpo/ff_vmpo.yaml
diff --git a/stoix/configs/system/ff_vmpo_continuous.yaml → ...onfigs/system/mpo/ff_vmpo_continuous.yaml b/stoix/configs/system/ff_vmpo_continuous.yaml → ...onfigs/system/mpo/ff_vmpo_continuous.yaml
diff --git a/stoix/configs/system/ff_dpo.yaml → stoix/configs/system/ppo/ff_dpo.yaml b/stoix/configs/system/ff_dpo.yaml → stoix/configs/system/ppo/ff_dpo.yaml
diff --git a/stoix/configs/system/ff_ppo.yaml → stoix/configs/system/ppo/ff_ppo.yaml b/stoix/configs/system/ff_ppo.yaml → stoix/configs/system/ppo/ff_ppo.yaml
diff --git a/stoix/configs/system/rec_ppo.yaml → stoix/configs/system/ppo/rec_ppo.yaml b/stoix/configs/system/rec_ppo.yaml → stoix/configs/system/ppo/rec_ppo.yaml
diff --git a/stoix/configs/system/ff_c51.yaml → stoix/configs/system/q_learning/ff_c51.yaml b/stoix/configs/system/ff_c51.yaml → stoix/configs/system/q_learning/ff_c51.yaml
diff --git a/stoix/configs/system/ff_dqn.yaml → stoix/configs/system/q_learning/ff_dqn.yaml b/stoix/configs/system/ff_dqn.yaml → stoix/configs/system/q_learning/ff_dqn.yaml
diff --git a/stoix/configs/system/ff_dqn_reg.yaml → ...configs/system/q_learning/ff_dqn_reg.yaml b/stoix/configs/system/ff_dqn_reg.yaml → ...configs/system/q_learning/ff_dqn_reg.yaml
diff --git a/stoix/configs/system/ff_mdqn.yaml → stoix/configs/system/q_learning/ff_mdqn.yaml b/stoix/configs/system/ff_mdqn.yaml → stoix/configs/system/q_learning/ff_mdqn.yaml
diff --git a/stoix/configs/system/ff_qr_dqn.yaml → .../configs/system/q_learning/ff_qr_dqn.yaml b/stoix/configs/system/ff_qr_dqn.yaml → .../configs/system/q_learning/ff_qr_dqn.yaml
diff --git a/stoix/configs/system/ff_rainbow.yaml → ...configs/system/q_learning/ff_rainbow.yaml b/stoix/configs/system/ff_rainbow.yaml → ...configs/system/q_learning/ff_rainbow.yaml
diff --git a/stoix/configs/system/ff_sac.yaml → stoix/configs/system/sac/ff_sac.yaml b/stoix/configs/system/ff_sac.yaml → stoix/configs/system/sac/ff_sac.yaml
diff --git a/stoix/configs/system/ff_az.yaml → stoix/configs/system/search/ff_az.yaml b/stoix/configs/system/ff_az.yaml → stoix/configs/system/search/ff_az.yaml
diff --git a/stoix/configs/system/ff_mz.yaml → stoix/configs/system/search/ff_mz.yaml b/stoix/configs/system/ff_mz.yaml → stoix/configs/system/search/ff_mz.yaml
diff --git a/stoix/configs/system/ff_sampled_az.yaml → .../configs/system/search/ff_sampled_az.yaml b/stoix/configs/system/ff_sampled_az.yaml → .../configs/system/search/ff_sampled_az.yaml
diff --git a/stoix/configs/system/ff_sampled_mz.yaml → .../configs/system/search/ff_sampled_mz.yaml b/stoix/configs/system/ff_sampled_mz.yaml → .../configs/system/search/ff_sampled_mz.yaml
diff --git a/stoix/configs/system/ff_reinforce.yaml → stoix/configs/system/vpg/ff_reinforce.yaml b/stoix/configs/system/ff_reinforce.yaml → stoix/configs/system/vpg/ff_reinforce.yaml