Loading scripts/exps/format/frozenlake/free_think/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading scripts/exps/format/frozenlake/grounding/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading scripts/exps/format/frozenlake/grounding_worldmodeling/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading scripts/exps/format/frozenlake/no_think/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading scripts/exps/format/frozenlake/worldmodeling/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading Loading
scripts/exps/format/frozenlake/free_think/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading
scripts/exps/format/frozenlake/grounding/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading
scripts/exps/format/frozenlake/grounding_worldmodeling/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading
scripts/exps/format/frozenlake/no_think/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading
scripts/exps/format/frozenlake/worldmodeling/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ algorithm.kl_ctrl.kl_coef=0.001 \ trainer.critic_warmup=0 \ trainer.logger=['console','wandb'] \ trainer.project_name='vagen_format' \ trainer.project_name='vagen_new' \ trainer.experiment_name=$EXPERIMENT_NAME \ trainer.n_gpus_per_node=4 \ trainer.nnodes=1 \ Loading
