Datasets:
messages listlengths 10 50 | metadata dict |
|---|---|
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a apple in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a apple in/on cabinet 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a keychain in/on desk 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a soapbottle in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a box in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on countertop 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pot in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 17
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a creditcard in/on laundryhamper 1.",
"room_type": "bedroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on bathtubbasin 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a knife in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a dishsponge in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a alarmclock in/on sidetable 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a plate in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a book in/on garbagecan 1.",
"room_type": "livingroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a candle in/on towelholder 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pencil in/on dresser 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pillow in/on garbagecan 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 17
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a saltshaker in/on coffeemachine 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a tissuebox in/on cabinet 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 27
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pen in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a soapbottle in/on garbagecan 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a tissuebox in/on desk 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a statue in/on drawer 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a towel in/on shelf 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pen in/on safe 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 21
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a candle in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a towel in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a tomato in/on fridge 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a cloth in/on sinkbasin 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 21
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pillow in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a mug in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a soapbar in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 21
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pot in/on toaster 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a watch in/on safe 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 23
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a candle in/on shelf 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a spoon in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a newspaper in/on garbagecan 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 23
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a candle in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a cd in/on shelf 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a plate in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a remotecontrol in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 25
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a spatula in/on countertop 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a creditcard in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 19
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a pan in/on toaster 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a scrubbrush in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a soapbar in/on towelholder 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a watch in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a statue in/on safe 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a spraybottle in/on countertop 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 17
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a tomato in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 21
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a creditcard in/on drawer 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 13
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a keychain in/on shelf 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a dishsponge in/on fridge 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 21
} |
[
{
"role": "system",
"content": "Interact with a household to solve a task. At each step, you will be given an observation from the environment. You should think about what to do next and then take an action. Available actions: go to {recep}, take {obj} from {recep}, put {obj} in/on {recep}, open {recep}, cl... | {
"task_type": "pick_and_place",
"description": "put a bowl in/on shelf 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
} |
YAML Metadata Warning: The task_categories "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
ALFWorld Trajectory Dataset
Overview
This is a synthetic SFT (Supervised Fine-Tuning) dataset designed for agent training in ALFWorld-compatible environments. The dataset programmatically generates expert trajectories without requiring an actual ALFWorld environment or a large language model.
Key Approach
- Template-based Simulation: Lightweight simulator based on published ALFWorld information (papers, ReAct prompt examples).
- Subgoal Decomposition: Rule-based expert system supporting 6 task types.
- Observation & Thought Diversity: Various templates for diversifying observation and thought texts.
- Multiple Formats: Supports both function-calling and ReAct formats.
Key Features
| Feature | Description |
|---|---|
| Compatibility | ALFWorld-compatible tasks and actions |
| Task Types | 6 distinct task types: pick_and_place, clean_and_place, heat_and_place, cool_and_place, examine, pick_two |
| Difficulty Levels | Easy, Normal, Hard (controlling exploration detours) |
| Trajectory Format | Function-calling (also available in ReAct format) |
| Multi-turn Dialogue | Each trajectory is a multi-turn conversation between user (observation) and assistant (thought, action) |
| Synthetic Data | Programmatically generated, ensuring controlled and varied scenarios |
Dataset Statistics
- Total trajectories: 1,200
- Average messages per trajectory: 21.1
- Number of steps (turns) distribution: 9 steps (3.3%) / 11 steps (4.9%) / 13 steps (8.8%) / 15 steps (12.6%) / 17 steps (14.4%) / 19 steps (10.6%) / 21 steps (11.5%) / 23 steps (8.9%) / 25 steps (8.2%) / 27 steps (4.8%) / 29 steps (3.9%) / 31 steps (2.8%) / 33 steps (1.2%) / 35 steps (0.9%) / 37 steps (0.7%) / 39 steps (0.9%) / 41 steps (0.5%) / 43 steps (0.3%) / 45 steps (0.5%) / 47 steps (0.2%) / 49 steps (0.1%)
- Task type distribution: clean_and_place: 200 (16.7%) / cool_and_place: 200 (16.7%) / examine: 200 (16.7%) / heat_and_place: 200 (16.7%) / pick_and_place: 200 (16.7%) / pick_two: 200 (16.7%)
- Difficulty distribution: Easy: 227 (18.9%) / Hard: 362 (30.2%) / Normal: 611 (50.9%)
Data Format
Each line in the JSONL file is a JSON object with the following fields:
{{ # Start of outer JSON object
"messages": [
{{"role": "system", "content": "Interact with a household to solve a task..."}},
{{"role": "user", "content": "You are in the middle of a room..."}},
{{"role": "assistant", "content": "Think: I should look for apple...",
"tool_calls": [
{{"id": "call_1", "type": "function", "function": {{ # Inner function object
"name": "act", "arguments": "{"action": "go to microwave 1"}"
}}}}
]
}},
{{"role": "tool", "tool_call_id": "call_1", "content": "The microwave 1 is open..."}}
// ... more turns
],
"metadata": {{ # Metadata object
"task_type": "heat_and_place",
"description": "put a hot apple in/on stoveburner 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
}}
}}
Usage
For SFT Training
from datasets import load_dataset
ds = load_dataset("u-10bei/sft_alfworld_trajectory_dataset")
for sample in ds["train"]:
messages = sample["messages"]
# messages is already in chat format for training
Last Updated
2026-02-10 00:24:11
License
MIT
- Downloads last month
- 682