Add Multi-GPU Support

[LovelyBuggies]

No description provided.

[LovelyBuggies]

Version 1.3.7 Results

Tests on TLDR

python train_magrpo.py --config configs/magrpo_tldr_config.yaml --override magrpo.parallel_training=none wandb.project=homo_tldr wandb.name=magrpo_tldr_1p7b_1p7b_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_magrpo.py --config configs/magrpo_tldr_config.yaml --override magrpo.parallel_training=mp mgrpo.agent_devices='[\"cuda:0\",\"cuda:1\"]' wandb.project=homo_tldr wandb.name=magrpo_tldr_1p7b_1p7b_2gpu

python train_maac.py --config configs/maac_tldr_config.yaml --override maac.parallel_training=None wandb.project=homo_tldr wandb.name=maac_tldr_1p7b_1p7b_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_maac.py --config configs/maac_tldr_config.yaml --override maac.parallel_training=mp maac.agent_devices='[\"cuda:0\",\"cuda:1\"]' maac.critic_devices='[\"cuda:0\"]' wandb.project=homo_tldr wandb.name=maac_tldr_1p7b_1p7b_2gpu

python train_iac.py --config configs/iac_tldr_config.yaml --override iac.parallel_training=none wandb.project=homo_tldr wandb.name=iac_tldr_1p7b_1p7b_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_iac.py --config configs/iac_tldr_config.yaml --override iac.parallel_training=mp iac.agent_devices='[\"cuda:0\",\"cuda:1\"]' iac.critic_devices='[\"cuda:0\",\"cuda:1\"]' wandb.project=homo_tldr wandb.name=iac_tldr_1p7b_1p7b_2gpu

Tests on CHE

python train_magrpo.py --config configs/magrpo_che_config.yaml --override magrpo.parallel_training=None agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' magrpo.agent_devices='[\"cuda:0\",\"cuda:1\"]' critic_model.name=None critics=None wandb.project=hetero_che wandb.name=magrpo_che_3b_4b_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_magrpo.py --config configs/magrpo_che_config.yaml --override magrpo.parallel_training=mp agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' magrpo.agent_devices='[\"cuda:0\",\"cuda:1\"]' critic_model.name=None critics=None wandb.project=hetero_che wandb.name=magrpo_che_3b_4b_2gpu

python train_maac.py --config configs/maac_che_config.yaml --override maac.parallel_training=none agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' critic_model.name=None critics='[\"Qwen/Qwen2.5-Coder-3B\"]' wandb.project=hetero_che wandb.name=maac_che_3b_4b_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_maac.py --config configs/maac_che_config.yaml --override maac.parallel_training=mp agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' maac.agent_devices='[\"cuda:0\",\"cuda:1\"]' maac.critic_devices='[\"cuda:0\"]' critic_model.name=None critics='[\"Qwen/Qwen2.5-Coder-3B\"]' wandb.project=hetero_che wandb.name=maac_che_3b_4b_2gpu

python train_iac.py --config configs/iac_che_config.yaml --override iac.use_separate_critic=false iac.parallel_training=none agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' critic_model.name=None critics=None wandb.project=hetero_che wandb.name=iac_che_3b_4b_share_1gpu

CUDA_VISIBLE_DEVICES=0,1 python train_iac.py --config configs/iac_che_config.yaml --override iac.use_separate_critic=false iac.parallel_training=mp agent_model.name=None agents='[\"Qwen/Qwen2.5-Coder-3B\",\"Qwen/Qwen3-4B-Instruct-2507\"]' iac.agent_devices='[\"cuda:0\",\"cuda:1\"]' critic_model.name=None critics=None wandb.project=hetero_che wandb.name=iac_che_3b_4b_share_2gpu

Tests on Minecraft

python house_build/train/train_magrpo.py --config house_build/configs/house_build_magrpo_config.yaml --override agents='[\"Qwen/Qwen2.5-3B-Instruct\",\"Qwen/Qwen3-4B-Instruct-2507\"]' magrpo.parallel_training=None agent_model.name=None critics=None critic_model.name=None wandb.project=hetero-mc wandb.name='magrpo_house_3B_4B_1gpu'

python house_build/train/train_maac.py --config house_build/configs/house_build_maac_config.yaml --override agents='[\"Qwen/Qwen2.5-3B-Instruct\",\"Qwen/Qwen3-4B-Instruct-2507\"]' maac.parallel_training=None agent_model.name=None critics='[\"Qwen/Qwen3-4B-Instruct-2507\"]' critic_model.name=None wandb.project=hetero-mc wandb.name='maac_house_3B_4B_1gpu'"

python house_build/train/train_maac.py --config house_build/configs/house_build_maac_config.yaml --override agents='[\"Qwen/Qwen2.5-3B-Instruct\",\"Qwen/Qwen3-4B-Instruct-2507\"]' maac.parallel_training=None agent_model.name=None critics='[\"Qwen/Qwen3-4B-Instruct-2507\"]' critic_model.name=None wandb.project=hetero-mc wandb.name='maac_house_3B_4B_1gpu