Loading README.md +0 −4 Original line number Diff line number Diff line Loading @@ -128,10 +128,6 @@ We present several cases selected from validation steps during training models w # Project Roadmap - 🗓️ Mar 25, 2025: We release VAGEN, a multi-turn reinforcement learning framework for training VLM Agents! - [ ] Merge to RAGEN for better package mangement - [ ] Address training stability issues - [ ] Lora Support - [ ] Implement improved early stopping and gradient clipping strategies - [ ] Reward normalization (refer to RAGEN) - [ ] Expand evaluation framework to more diverse visual environments - [ ] Scaling to larger models and applying TRICO to text-only tasks Loading docs/reproduce-exp.md +1 −1 Original line number Diff line number Diff line Loading @@ -14,7 +14,7 @@ bash vagen/examples/release_experiments/gae.sh # rico-gae bash vagen/examples/release_experiments/grpo_mask_loss.sh # rico-grpo + loss mask bash vagen/examples/release_experiments/grpo.sh # rico-grpo bash vagen/examples/release_experiments/mask_gae_mask_loss_bi_level.sh # trico - turn reward bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_gae.sh # trico - turn reward - bi-level gae + turn-level gae bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_gae.sh # trico - turn reward - bi-level gae bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_reward_bi_level.sh # trico bash vagen/examples/release_experiments/mask_gae_mask_loss.sh # aico bash vagen/examples/release_experiments/mask_gae.sh # aico - loss mask Loading vagen/env/README.md +4 −1 Original line number Diff line number Diff line Loading @@ -15,6 +15,9 @@ apt-get install -y xorg xserver-xorg-core xserver-xorg-video-dummy python vagen/env/navigation/startx.py 1 ``` ### Maniskill ### Manipulation ``` pip install --upgrade mani_skill python -m mani_skill.utils.download_asset "PickSingleYCB-v1" python -m mani_skill.utils.download_asset partnet_mobility_cabinet ``` Loading
README.md +0 −4 Original line number Diff line number Diff line Loading @@ -128,10 +128,6 @@ We present several cases selected from validation steps during training models w # Project Roadmap - 🗓️ Mar 25, 2025: We release VAGEN, a multi-turn reinforcement learning framework for training VLM Agents! - [ ] Merge to RAGEN for better package mangement - [ ] Address training stability issues - [ ] Lora Support - [ ] Implement improved early stopping and gradient clipping strategies - [ ] Reward normalization (refer to RAGEN) - [ ] Expand evaluation framework to more diverse visual environments - [ ] Scaling to larger models and applying TRICO to text-only tasks Loading
docs/reproduce-exp.md +1 −1 Original line number Diff line number Diff line Loading @@ -14,7 +14,7 @@ bash vagen/examples/release_experiments/gae.sh # rico-gae bash vagen/examples/release_experiments/grpo_mask_loss.sh # rico-grpo + loss mask bash vagen/examples/release_experiments/grpo.sh # rico-grpo bash vagen/examples/release_experiments/mask_gae_mask_loss_bi_level.sh # trico - turn reward bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_gae.sh # trico - turn reward - bi-level gae + turn-level gae bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_gae.sh # trico - turn reward - bi-level gae bash vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_reward_bi_level.sh # trico bash vagen/examples/release_experiments/mask_gae_mask_loss.sh # aico bash vagen/examples/release_experiments/mask_gae.sh # aico - loss mask Loading
vagen/env/README.md +4 −1 Original line number Diff line number Diff line Loading @@ -15,6 +15,9 @@ apt-get install -y xorg xserver-xorg-core xserver-xorg-video-dummy python vagen/env/navigation/startx.py 1 ``` ### Maniskill ### Manipulation ``` pip install --upgrade mani_skill python -m mani_skill.utils.download_asset "PickSingleYCB-v1" python -m mani_skill.utils.download_asset partnet_mobility_cabinet ```
