trajectory_idx int64 0 705 | turn_idx int64 0 22 | prompt_messages listlengths 2 46 | reference_response stringlengths 53 139 | reference_action stringlengths 11 40 | previous_action stringclasses 66
values | admissible_actions listlengths 9 30 | action_rewards listlengths 9 30 | metadata dict |
|---|---|---|---|---|---|---|---|---|
0 | 0 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: First, I should locate apple. toaster 1 seems like a good place to look.
Act: go to toaster 1 | go to toaster 1 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to she... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... | |
0 | 1 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I spot apple 99 on stoveburner 1. Let me take it.
Act: take apple 99 from stoveburner 1 | take apple 99 from stoveburner 1 | go to toaster 1 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to she... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... |
0 | 3 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: No sign of apple. I'll check shelf 4.
Act: go to shelf 4 | go to shelf 4 | go to countertop 3 | [
"go to countertop 1",
"go to countertop 2",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to shelf 4",
"go to shelf 5"... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"act... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... |
0 | 4 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Still searching for apple. Moving to stoveburner 1.
Act: go to stoveburner 1 | go to stoveburner 1 | go to shelf 4 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to she... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... |
0 | 5 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Found it! apple 1 is on stoveburner 1. Let me pick it up.
Act: take apple 1 from stoveburner 1 | take apple 1 from stoveburner 1 | go to stoveburner 1 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to shelf 4",
"go to shelf 5",... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... |
0 | 7 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I'll drop apple 1 here.
Act: put apple 1 in/on sinkbasin 1 | put apple 1 in/on sinkbasin 1 | go to sinkbasin 1 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to fridge 1",
"go to microwave 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to shelf 4",
"go to shelf 5... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{... | {
"description": "place a apple on the sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": true,
"num_actions": 8,
"num_detours": 3,
"num_observations": 9,
"num_recovery_steps": 1,
"num_st... |
1 | 0 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I wonder if showerglass is at bathtubbasin 1. Let me check.
Act: go to bathtubbasin 1 | go to bathtubbasin 1 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to countertop 1",
"go to countertop 2",
"go to shelf 1",
"go to shelf 2",
"go to towelholder 1",
"go to garbagecan 1",
"go to drawer 1",
"go to drawer 2",
"go to dr... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 0
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0
},
{
"act... | {
"description": "locate a showerglass and place it in/on sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 2,
"num_observations": 7,
"num_recovery_... | |
1 | 1 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Not here. Moving on to towelholder 1.
Act: go to towelholder 1 | go to towelholder 1 | go to bathtubbasin 1 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to countertop 1",
"go to countertop 2",
"go to shelf 1",
"go to shelf 2",
"go to towelholder 1",
"go to garbagecan 1",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action":... | {
"description": "locate a showerglass and place it in/on sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 2,
"num_observations": 7,
"num_recovery_... |
1 | 2 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Nothing useful here. Let me move to shelf 2.
Act: go to shelf 2 | go to shelf 2 | go to towelholder 1 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to countertop 1",
"go to countertop 2",
"go to shelf 1",
"go to shelf 2",
"go to garbagecan 1",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer ... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0
},
{
"act... | {
"description": "locate a showerglass and place it in/on sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 2,
"num_observations": 7,
"num_recovery_... |
1 | 3 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: There's showerglass 1 here. Let me take it.
Act: take showerglass 1 from shelf 2 | take showerglass 1 from shelf 2 | go to shelf 2 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to countertop 1",
"go to countertop 2",
"go to shelf 1",
"go to towelholder 1",
"go to garbagecan 1",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to d... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
... | {
"description": "locate a showerglass and place it in/on sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 2,
"num_observations": 7,
"num_recovery_... |
1 | 5 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I'll set showerglass 1 in/on sinkbasin 1.
Act: put showerglass 1 in/on sinkbasin 1 | put showerglass 1 in/on sinkbasin 1 | go to sinkbasin 1 | [
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to countertop 1",
"go to countertop 2",
"go to shelf 1",
"go to shelf 2",
"go to towelholder 1",
"go to garbagecan 1",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawe... | [
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
... | {
"description": "locate a showerglass and place it in/on sinkbasin 1.",
"difficulty": "normal",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": false,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 2,
"num_observations": 7,
"num_recovery_... |
2 | 0 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Finding showerglass is the first step. Let me head to sinkbasin 1.
Act: go to sinkbasin 1 | go to sinkbasin 1 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shel... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"act... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... | |
2 | 1 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: showerglass wasn't there. Let me try cabinet 6.
Act: go to cabinet 6 | go to cabinet 6 | go to sinkbasin 1 | [
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to towelhol... | [
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"actio... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
2 | 2 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: The cabinet 6 is shut. Opening it now.
Act: open cabinet 6 | open cabinet 6 | go to cabinet 6 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to towelh... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
2 | 4 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Let me open the cabinet 3 and check inside.
Act: open cabinet 3 | open cabinet 3 | go to cabinet 3 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to towelh... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
2 | 6 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Not what I'm looking for. toilet 1 is next.
Act: go to toilet 1 | go to toilet 1 | go to garbagecan 1 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shel... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"act... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
2 | 7 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: showerglass is not here. Let me check countertop 2.
Act: go to countertop 2 | go to countertop 2 | go to toilet 1 | [
"go to sinkbasin 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to towel... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"ac... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
2 | 8 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Still can't locate showerglass after searching several receptacles.
Act: go to cabinet 2 | go to cabinet 2 | go to countertop 2 | [
"go to sinkbasin 1",
"go to toilet 1",
"go to bathtubbasin 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to cabinet 5",
"go to cabinet 6",
"go to countertop 1",
"go to countertop 3",
"go to shelf 1",
"go to shelf 2",
"go to shelf 3",
"go to towelhold... | [
{
"action": "go to sinkbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to toilet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to bathtubbasin 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"act... | {
"description": "put a showerglass in/on shelf 1.",
"difficulty": "hard",
"failure_reason": "search_exhausted",
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 9,
"num_detours": 7,
"num_observations": 10,
"num_recovery_steps": ... |
3 | 0 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I need saltshaker for this task. Let me look at shelf 1.
Act: go to shelf 1 | go to shelf 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... | |
3 | 1 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: saltshaker is not at this location. I'll try coffeemachine 1 next.
Act: go to coffeemachine 1 | go to coffeemachine 1 | go to shelf 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 2 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Still searching for saltshaker. Moving to sinkbasin 1.
Act: go to sinkbasin 1 | go to sinkbasin 1 | go to coffeemachine 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 3 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Still looking for saltshaker. Let me search drawer 4.
Act: go to drawer 4 | go to drawer 4 | go to sinkbasin 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer 6... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 4 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Let me open the drawer 4 first.
Act: open drawer 4 | open drawer 4 | go to drawer 4 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 5",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 5 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Still searching for saltshaker. Moving to cabinet 1.
Act: go to cabinet 1 | go to cabinet 1 | open drawer 4 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 5",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 6 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: The cabinet 1 is closed. I need to open it first.
Act: open cabinet 1 | open cabinet 1 | go to cabinet 1 | [
"go to countertop 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 3",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 7 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I don't see saltshaker here. I'll try microwave 1 next.
Act: go to microwave 1 | go to microwave 1 | open cabinet 1 | [
"go to countertop 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 3",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 8 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Can't see anything - the microwave 1 is closed. Let me open it.
Act: open microwave 1 | open microwave 1 | go to microwave 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer 6... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"acti... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 9 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Let me try cabinet 2 next. saltshaker should be around.
Act: go to cabinet 2 | go to cabinet 2 | open microwave 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer 6... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 1
},
{
"acti... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 10 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: I can see saltshaker 1 on cabinet 2. I'll grab it.
Act: take saltshaker 1 from cabinet 2 | take saltshaker 1 from cabinet 2 | go to cabinet 2 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawer 5",
"go to drawer... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 3",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
3 | 12 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: Let me deposit saltshaker 1 in/on garbagecan 1.
Act: put saltshaker 1 in/on garbagecan 1 | put saltshaker 1 in/on garbagecan 1 | go to garbagecan 1 | [
"go to countertop 1",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to drawer 1",
"go to drawer 2",
"go to drawer 3",
"go to drawer 4",
"go to drawe... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 1",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"action": "go to cabinet 2",
"is_repeat": false,
"reason": "",
"reward": 0.5
},
{
"... | {
"description": "put a saltshaker in/on garbagecan 1.",
"difficulty": "hard",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 13,
"num_detours": 6,
"num_observations": 14,
"num_recovery_steps": 0,
"num... |
4 | 0 | [
{
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action.",
"role": "system"
},
... | Think: My goal requires peppershaker. Let me try drawer 5.
Act: go to drawer 5 | go to drawer 5 | [
"go to countertop 1",
"go to countertop 2",
"go to countertop 3",
"go to cabinet 1",
"go to cabinet 2",
"go to cabinet 3",
"go to cabinet 4",
"go to fridge 1",
"go to microwave 1",
"go to sinkbasin 1",
"go to stoveburner 1",
"go to stoveburner 2",
"go to stoveburner 3",
"go to drawer 1",
... | [
{
"action": "go to countertop 1",
"is_repeat": false,
"reason": "",
"reward": 1.5
},
{
"action": "go to countertop 2",
"is_repeat": false,
"reason": "",
"reward": 1.5
},
{
"action": "go to countertop 3",
"is_repeat": false,
"reason": "",
"reward": 1.5
},
{... | {
"description": "locate a peppershaker and place it in/on cabinet 1.",
"difficulty": "easy",
"failure_reason": null,
"has_admissible": true,
"has_close_open": false,
"has_open_action": true,
"has_recovery_steps": false,
"num_actions": 6,
"num_detours": 0,
"num_observations": 7,
"num_recovery_step... |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 10