state listlengths 2 24 | action dict | next_obs listlengths 2 2 | state_len int64 1.88k 3.22k | temperature float64 1 1 | reward float64 0.13 1 | done bool 2
classes | truncated bool 1
class | timestep int64 0 11 | try_step int64 0 0 | batch_id int64 90 90 | unique_data_sample_id int64 0 79 | generation_id int64 0 0 | split stringclasses 1
value | return_ float64 0.13 1 | advantage float64 0.13 1 | return_is_computed bool 1
class | advantage_is_computed bool 1
class | constant_reward_group bool 1
class | tools listlengths 11 11 | action_prob float64 0.13 1 | system_prompt null |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I am in a bedroom. The task is to take the broom. I need to check what items are visible in the room to locate the broom. I'll use the \"look\" command to examine the surroundings carefully.\n\n<tool_call>\n{\"name\": \"look\", \"arguments\": {}}\n</tool_call>",
"role": "assistant"
} | [
{
"content": "-= Bedroom =-\nYou are in a bedroom. A typical kind of place.\n\n\n\nThere is an unblocked exit to the east. There is an unguarded exit to the west.\n\n\n> -= Bedroom =-0/... | 1,900 | 1 | 1 | false | false | 0 | 0 | 90 | 0 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The broom is not visible in the current room. Since there is an unguarded exit to the west, I'll explore that direction to find the broom. Moving west might lead to a room where the broom is located or a place where I can find it. I need to explore further.\n\n<tool_call>\n{\"name\": \"go\", \"arguments... | [
{
"content": "-= Basement =-\nYou arrive in a basement. A normal one.\n\n\n\nYou don't like doors? Why not try going east, that entranceway is unguarded. You don't like doors? Why not try going south, that entranceway is unguarded.\n\nThere is a broom and a fly larva on the floor.\n\n\n> ... | 2,133 | 1 | 1 | false | false | 1 | 0 | 90 | 0 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I found the broom in the basement. I will take it to complete the task. The objective is to take the broom, and once I have it, the score should update to 1, indicating the task is completed.\n\n<tool_call>\n{\"name\": \"take\", \"arguments\": {\"item\": \"broom\"}}\n</tool_call>",
"role": "assistant"... | [
{
"content": "",
"role": "assistant"
},
{
"content": "",
"role": "assistant"
}
] | 2,289 | 1 | 1 | true | false | 2 | 0 | 90 | 0 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I need to explore the bar environment to find the latchkey. The initial look might reveal visible items or clues. I'll check the surroundings to locate the latchkey.\n\n<tool_call>\n{\"name\": \"look\", \"arguments\": {}}\n</tool_call>",
"role": "assistant"
} | [
{
"content": "-= Bar =-\nYou've entered a bar.\n\n\n\nYou don't like doors? Why not try going north, that entranceway is unguarded.\n\n\n> -= Bar =-0/2\n\n## Current State:\n\n{\n \"cu... | 1,886 | 1 | 1 | false | false | 0 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The bar has a north entrance that is unguarded. I will move north to explore further, as the latchkey might be in a new area. This is a logical step to continue my search for the required item.\n\n<tool_call>\n{\"name\": \"go\", \"arguments\": {\"direction\": \"north\"}}\n</tool_call>",
"role": "assis... | [
{
"content": "-= Kitchen =-\nWell, here we are in the kitchen.\n\n\n\nThere is an exit to the east. Don't worry, it is unblocked. There is an unblocked exit to the south.\n\n\n> -= Kitc... | 2,093 | 1 | 1 | false | false | 1 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I am now in the kitchen. I need to look around to see if the latchkey is visible or if there's any container or object where it might be stored. I'll perform a detailed look to find the latchkey.\n\n<tool_call>\n{\"name\": \"look\", \"arguments\": {}}\n</tool_call>",
"role": "assistant"
} | [
{
"content": "-= Kitchen =-\nWell, here we are in the kitchen.\n\n\n\nThere is an exit to the east. Don't worry, it is unblocked. There is an unblocked exit to the south.\n\n\n> -= Kitc... | 2,192 | 1 | 1 | false | false | 2 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The kitchen has an exit to the east. I will move east to explore that area, as the latchkey might be located there. This is a logical next step to locate the object required for the task.\n\n<tool_call>\n{\"name\": \"go\", \"arguments\": {\"direction\": \"east\"}}\n</tool_call>",
"role": "assistant"
} | [
{
"content": "-= Bedchamber =-\nYou arrive in a bedchamber. An ordinary kind of place. The room seems oddly familiar, as though it were only superficially different from the other rooms in the building.\n\n\n\nYou don't like doors? Why not try going south, that entranceway is unguarded. There is an unblocked ex... | 2,265 | 1 | 1 | false | false | 3 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I am now in the bedchamber. I need to check if the latchkey is visible or if it's inside any containers or on furniture. A detailed look might reveal the item or give clues about where to find it. I'll perform another look to gather more information.\n\n<tool_call>\n{\"name\": \"look\", \"arguments\": {... | [
{
"content": "-= Bedchamber =-\nYou arrive in a bedchamber. An ordinary kind of place. The room seems oddly familiar, as though it were only superficially different from the other rooms in the building.\n\n\n\nYou don't like doors? Why not try going south, that entranceway is unguarded. There is an unblocked ex... | 2,404 | 1 | 1 | false | false | 4 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The bedchamber has a south exit that is unguarded. I will move south to explore further, as the latchkey might be in a new area. This is a logical step to continue my search for the required item. I will check the next room to see if the latchkey is visible or stored somewhere.\n\n<tool_call>\n{\"name\"... | [
{
"content": "-= Workshop =-\nYou've just sauntered into a workshop.\n\n\n\nYou don't like doors? Why not try going east, that entranceway is unblocked. There is an unguarded exit to the north.\n\nThere is a gummy bear and a latchkey on the floor.\n\n\n> ... | 2,487 | 1 | 1 | false | false | 5 | 0 | 90 | 1 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I found the latchkey on the floor of the workshop. Now that I have it, I can complete the task. The objective was to take the latchkey, and I have successfully acquired it. The score should now reflect completion of the task.\n\n<tool_call>\n{\"name\": \"take\", \"arguments\": {\"item\": \"latchkey\"}}\... | [
{
"content": "",
"role": "assistant"
},
{
"content": "",
"role": "assistant"
}
] | 2,556 | 1 | 0.80856 | true | false | 6 | 0 | 90 | 1 | 0 | train_all | 0.80856 | 0.80856 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 0.80856 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I need to explore the shower room more thoroughly to find the passkey or any clues related to the objective. I'll use the look command to get a detailed description of the current room, which might reveal hidden items or exits. This is crucial because the passkey was previously taken from the cellar, an... | [
{
"content": "-= Shower =-\nYou find yourself in a shower. A normal kind of place. You begin to take stock of what's in the room.\n\n\n\nYou need an unblocked exit? You should try going east. You need an unblocked exit? You should try going south.\n\n\n> ... | 1,938 | 1 | 1 | false | false | 0 | 0 | 90 | 2 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The shower has exits to the east and south. I need to explore further to find the passkey or the refrigerator. Since the passkey is required for the task, I'll try going east first to see if it leads to a room with the teapot or where I can find the refrigerator. This will help me progress toward comple... | [
{
"content": "-= Cellar =-\nYou arrive in a cellar. An usual kind of place.\n\n\n\nThere is an exit to the south. Don't worry, it is unguarded. You need an unblocked exit? You should try going west.\n\n\n> ... | 2,238 | 1 | 1 | false | false | 1 | 0 | 90 | 2 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I moved to the cellar and noticed there's an exit to the south and a suggestion to go west. Since I need to find the passkey or complete the objective, I will go west to explore further. This path might lead to a room with the refrigerator or the teapot. I need to continue exploring systematically to lo... | [
{
"content": "-= Chamber =-\nYou are in a chamber. A standard kind of place.\n\n\n\nYou don't like doors? Why not try going north, that entranceway is unguarded.\n\nThere is a passkey on the floor.\n\n\n> ... | 2,326 | 1 | 0.357801 | false | false | 2 | 0 | 90 | 2 | 0 | train_all | 0.357801 | 0.357801 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 0.357801 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I found another passkey in the chamber. Since the objective is to recover the teapot from the refrigerator, and I now have a passkey, I need to determine if this passkey can be used to access the refrigerator. I will keep the passkey in my inventory and look for the refrigerator or a door that requires ... | [
{
"content": "",
"role": "assistant"
},
{
"content": "",
"role": "assistant"
}
] | 2,422 | 1 | 1 | true | false | 3 | 0 | 90 | 2 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I need to gather more information about the studio. I should look around to see if I can find the refrigerator or any clues about where the teapot might be. The passkey is still in my inventory, and I need to use it wisely. I'll perform a full look to assess the environment.\n\n<tool_call>\n{\"name\": \... | [
{
"content": "-= Studio =-\nThis might come as a shock to you, but you've just entered a studio.\n\n\n\nYou don't like doors? Why not try going north, that entranceway is unblocked. You need an unguarded exit? You should try going south. You don't like doors? Why not try going west, that entranceway is unblocke... | 1,972 | 1 | 1 | false | false | 0 | 0 | 90 | 3 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I need to explore the studio more systematically. North is unblocked, so I'll go there first to see if there's a refrigerator or any relevant object. I'll continue exploring from there to locate the teapot.\n\n<tool_call>\n{\"name\": \"go\", \"arguments\": {\"direction\": \"north\"}}\n</tool_call>",
"... | [
{
"content": "-= Cookery =-\nYou arrive in a cookery. A normal kind of place. You can barely contain your excitement.\n\n\n\nYou don't like doors? Why not try going south, that entranceway is unguarded.\n\nThere is a passkey on the floor.\n\n\n> ... | 2,292 | 1 | 1 | false | false | 1 | 0 | 90 | 3 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I found another passkey in the cookery. I now have two passkeys, but I still need to find the refrigerator to recover the teapot. I'll keep this one in my inventory and continue exploring to locate the refrigerator or any relevant area. I'll go south from here to keep progressing.\n\n<tool_call>\n{\"nam... | [
{
"content": "",
"role": "assistant"
},
{
"content": "",
"role": "assistant"
}
] | 2,334 | 1 | 0.87671 | true | false | 2 | 0 | 90 | 3 | 0 | train_all | 0.87671 | 0.87671 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 0.87671 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "I am now in the Chamber. Before moving, I should check what objects are visible in the room to see if the fondue is present or if I can find a path to it. This will help me plan my next steps effectively.\n\n<tool_call>\n{\"name\": \"look\", \"arguments\": {}}\n</tool_call>",
"role": "assistant"
} | [
{
"content": "-= Chamber =-\nYou're now in the chamber. You decide to just list off a complete list of everything you see in the room, because hey, why not?\n\n\n\nYou need an unguarded exit? You should try going east. You don't like doors? Why not try going north, that entranceway is unguarded.\n\n\n> ... | 1,960 | 1 | 0.377867 | false | false | 0 | 0 | 90 | 4 | 0 | train_all | 0.377867 | 0.377867 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 0.377867 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The chamber has an unguarded exit to the east. I will go east to explore and see if the fondue is located there or if it's in a room that leads to it. This is a logical next step to progress toward completing the task of retrieving the fondue.\n\n<tool_call>\n{\"name\": \"go\", \"arguments\": {\"directi... | [
{
"content": "-= Cookhouse =-\nYou have fallen into the most typical of all possible cookhouses.\n\n\n\nYou need an unguarded exit? You should try going west.\n\nThere is a fondue on the floor.\n\n\n> ... | 2,255 | 1 | 1 | false | false | 1 | 0 | 90 | 4 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
[
{
"content": "You are a helpful tool-calling assistant.\n\nYou are an agent playing TextWorld, a text-based adventure game where you are in a randomly generated maze and must find a specific object.\nYou need to explore different rooms to find the target object.\n\n## Rules:\n- You need to unlock a locked door ... | {
"content": "The fondue is on the floor in the Cookhouse. I need to take it to complete the task. Once I have the fondue, the objective will be fulfilled, and my score will update to 1, indicating success.\n\n<tool_call>\n{\"name\": \"take\", \"arguments\": {\"item\": \"fondue\"}}\n</tool_call>",
"role": "assistan... | [
{
"content": "",
"role": "assistant"
},
{
"content": "",
"role": "assistant"
}
] | 2,295 | 1 | 1 | true | false | 2 | 0 | 90 | 4 | 0 | train_all | 1 | 1 | true | true | false | [
{
"description": "Describe the current room.",
"name": "look",
"parameters": {
"properties": {
"container": null,
"direction": null,
"item": null,
"key": null,
"source": null,
"supporter": null,
"target": null
},
"required": [],
... | 1 | null |
End of preview. Expand in Data Studio
Act-PRM Rollout Dataset
Run Metadata
- run_name:
act-prm-v2-ia=0-rr=0-ec=act_prm_tw_treasure_easy_gpt5m-gc=aprm_qwen3_ap-tc=aprm_for_sft100-rbc=default-mc=hf_qwen3_4b_inst_2507-lc=r8_a16_qkvo-nf=0-ao=1-ho=1-gs=8-bs=8-lr=4e_05-ns=4-s=0-r=gpt5m_hd_0 - run_cmd:
main_pytorch.py --env_config act_prm/tw_treasure_easy_gpt5m --model_config hf_qwen3_4b_inst_2507 --lora_config r8_a16_qkvo --generator_config aprm_qwen3_ap --trainer_config aprm_for_sft100 --replay_buffer_config default --log_path ./logs --actions_only --hide_observations --batch_size 8 --group_size 8 --learning_rate 4e-5 --num_substeps 4 --seed 0 --replicate gpt5m_hd_0 --verbose - batch_idx:
90 - split:
train_all - trajectory_key:
think_act_policy - num_trajectories:
348 - num_episodes:
348 - group_size:
8 - batch_size:
8
- Downloads last month
- 29