TASK=alfworld         # alfworld, alfworld_valid_seen, alfworld_valid_unseen, sciworld, textworld, webshop, stabletoolbench
MODEL=X1AOX1A/WorldModel-Alfworld-Qwen2.5-7B                  # world model checkpoint
OUTPUT_ROOT=outputs/single_step_accuracy/${TASK}/${MODEL}     # output root directory
bash scripts/single_step_accuracy/run.sh $TASK $MODEL $OUTPUT_ROOT

Example output:

{
    "average_accuracy": 0.9987087517934002
}

TASK=alfworld         # alfworld, sciworld, textworld, webshop
RUN=0                 # run id for multiple runs, just for separating output dirs
API_KEY=your_api_key  # your OpenAI API key
API_BASE_URL=your_api_base_url # your OpenAI API base URL
MODEL=gpt-4o          # agent model name
MAX_CONCURRENCY=150   # max concurrency
MAX_ROUND=50          # max round
NUM_EXAMPLES=-1       # num examples
SPLIT=test            # train, test (and valid_seen, valid_unseen for ALFWorld only)
OUTPUT_ROOT=outputs   # output root directory
# this will auto-launch the environment server
bash scripts/interact_with_real_env/run_openai.sh $TASK $RUN $API_KEY $API_BASE_URL $MODEL $MAX_CONCURRENCY $MAX_ROUND $NUM_EXAMPLES $SPLIT $OUTPUT_ROOT
# metrics will be saved to outputs/interaction/real_env/$SPLIT/${TASK}/$MODEL/${TASK}_maxround${MAX_ROUND}_run${RUN}/_metrics.json

Example output:

{
    "accuracy": 50.50,  # task success rate
    "success": 101.0,   # total successful interactions
    "api_errors": 0,    # API errors
    "total": 200,       # total interactions
    "time_seconds": 1075.621458530426  # time taken in seconds
}

TASK=alfworld         # alfworld, sciworld, textworld, webshop
RUN=0                 # run id for multiple runs, just for separating output dirs
MODEL=Qwen/Qwen2.5-7B-Instruct       # agent model name
MAX_CONCURRENCY=150   # max concurrency
MAX_ROUND=20          # max round, reduce to 20 to prevent exceeding the context length
NUM_EXAMPLES=-1       # num examples
SPLIT=test            # train, test (and valid_seen, valid_unseen for ALFWorld only)
OUTPUT_ROOT=outputs   # output root directory
# this will auto-launch the vLLM server and the environment server
bash scripts/interact_with_real_env/run_vllm.sh $TASK $RUN $MODEL $MAX_CONCURRENCY $MAX_ROUND $NUM_EXAMPLES $SPLIT $OUTPUT_ROOT
# metrics will be saved to outputs/interaction/real_env/$SPLIT/vllm/${TASK}/$MODEL/${TASK}_maxround${MAX_ROUND}_run${RUN}/_metrics.json

TASK=alfworld         # alfworld, sciworld, textworld, webshop
MODEL=gpt-4o          # agent model name
API_KEY=your_api_key  # your OpenAI API key
API_BASE_URL=your_api_base_url # your OpenAI API base URL
WORLD_MODEL=X1AOX1A/WorldModel-Alfworld-Qwen2.5-7B # world model checkpoint
MAX_CONCURRENCY=150   # max concurrency
MAX_ROUND=50          # max round
NUM_EXAMPLES=-1       # num examples
SPLIT=test            # train, test (and valid_seen, valid_unseen for ALFWorld only)
OUTPUT_ROOT=outputs   # output root directory
# this will auto-launch the vLLM server for the world model
bash scripts/interact_with_world_model/run.sh $TASK $MODEL $API_KEY $API_BASE_URL $WORLD_MODEL $MAX_CONCURRENCY $MAX_ROUND $NUM_EXAMPLES $SPLIT $OUTPUT_ROOT
# metrics will be saved to outputs/interaction/world_model/$SPLIT/$TASK/$MODEL/$WORLD_MODEL/$MODEL/_metrics.json

Example output:

{
    "task": "alfworld",                    # task name
    "agent_model": "gpt-4o",               # agent model name
    "total_items": 200,                    # total items
    "total_success": 109.0,                # total successful interactions
    "processed_items": 200,                # processed items
    "accuracy": 54.50000000000001,         # task success rate
    "api_errors": 0                        # API errors
}

TASK=alfworld                 # alfworld, alfworld_valid_seen, alfworld_valid_unseen, sciworld, textworld, webshop
TEST_FILE_ROOT=test_file_root # e.g. outputs/interaction/world_model/${SPLIT}/${TASK}/${MODEL}/${WORLD_MODEL}/${MODEL}
MAX_WORKERS=50                # max workers, set to 1 for textworld
# this will auto-launch the environment server
bash scripts/interact_with_world_model/cal_wm2real.sh $TASK $TEST_FILE_ROOT $MAX_WORKERS
# metrics will be saved to $TEST_FILE_ROOT/valid_on_real_env/_metrics.json

Example output:

{
    "total": 200,                # total items
    "processed": 200,            # processed items
    "success": 111,              # total successful interactions
    "errors": 0,                 # API errors
    "accuracy": 0.555            # task success rate
}

### model
model_name_or_path: Qwen/Qwen2.5-7B
trust_remote_code: true

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: src/LLaMA-Factory/examples/deepspeed/ds_z2_config.json  # choices: [ds_z0_config.json, ds_z2_config.json, ds_z3_config.json]

### dataset
dataset_dir: data/llama_factory
dataset: alfworld_train_with_env_54006
template: qwen
cutoff_len: 12288
max_samples: 40000    # 40K for ALFWorld, SciWorld, TextWorld; 70K for Webshop; 160K for StableToolBench
overwrite_cache: true
preprocessing_num_workers: 16
dataloader_num_workers: 4

### output
output_dir: outputs/ckpt/alfworld/qwen2.5_7b/alfworld_train_with_env_40k
logging_steps: 1
save_steps: 160
plot_loss: true
overwrite_output_dir: true
save_only_model: false
report_to: wandb  # choices: [none, wandb, tensorboard, swanlab, mlflow]

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 16
learning_rate: 1.0e-5
num_train_epochs: 5.0
lr_scheduler_type: constant_with_warmup
warmup_steps: 10
bf16: true
ddp_timeout: 180000000
resume_from_checkpoint: null
max_grad_norm: 100