chore: add more algs to run script

EdanToledo · Sep 20, 2024 · 1e70fa3 · 1e70fa3
1 parent eacedbf
commit 1e70fa3
Showing 1 changed file with 5 additions and 0 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