Datasets:

novastar112
/

toy_maze_2d_train_allstep_thinking_future_rollout_cot

Tasks:

Image-to-Text

Reinforcement Learning

License:

Dataset card Data Studio Files Files and versions

xet

Community

Dataset Preview

Duplicate

Split (1)

train

The full dataset viewer is not available (click to read why). Only showing a preview of the rows.

The dataset generation failed

Error code:   DatasetGenerationError
Exception:    ValueError
Message:      Expected object or value
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1779, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 237, in _generate_tables
                  examples = [ujson_loads(line) for line in batch.splitlines()]
                              ^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/utils/json.py", line 20, in ujson_loads
                  return pd.io.json.ujson_loads(*args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
              ValueError: Expected object or value
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1347, in compute_config_parquet_and_info_response
                  parquet_operations = convert_to_parquet(builder)
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
                  builder.download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 882, in download_and_prepare
                  self._download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 943, in _download_and_prepare
                  self._prepare_split(split_generator, **prepare_split_kwargs)
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1646, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1832, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

schema_version string	synth_status string	cot_row_type string	task string	difficulty string	split string	trajectory_index int64	source_path string	trajectory_length int64	selected_steps list	stop_step int64	chosen_actions list	answer string	messages list	trajectory_steps list	source_record dict	interleaved_cot dict	stop_cot dict	stats dict	metadata dict	hash string
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	0	toy_maze_2d/train/batch_000000.jsonl	23	[ 3, 8 ]	22	[ "('move', 3)", "('move', 0)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 3)","vlm_output":"<think></think><answer>('move', 3)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[7,17],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"t(...TRUNCATED)	{ "assistant_turn_index": 45, "action": "('stop', 'stop')" }	{ "step": 23, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	60c38441c98ebb9f35c80a5ec891dfa5212939acccb1f6fecffdb0bd7b23d92f
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	1	toy_maze_2d/train/batch_000000.jsonl	19	[ 3, 16 ]	18	[ "('move', 2)", "('move', 2)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 3)","vlm_output":"<think></think><answer>('move', 3)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[7,33],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"t(...TRUNCATED)	{ "assistant_turn_index": 37, "action": "('stop', 'stop')" }	{ "step": 19, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	d87a2de1890262692c00b61f50322ad4808c5c80a198fac1628402802a9ace71
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	2	toy_maze_2d/train/batch_000000.jsonl	21	[ 10, 11 ]	20	[ "('move', 2)", "('move', 2)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 2)","vlm_output":"<think></think><answer>('move', 2)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[21,23],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"(...TRUNCATED)	{ "assistant_turn_index": 41, "action": "('stop', 'stop')" }	{ "step": 21, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	92e6d005ebc96d82de487e88319139543a6da73b72d5569ae32073263369856a
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	3	toy_maze_2d/train/batch_000000.jsonl	23	[ 5, 21 ]	22	[ "('move', 3)", "('move', 3)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 3)","vlm_output":"<think></think><answer>('move', 3)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[11,43],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"(...TRUNCATED)	{ "assistant_turn_index": 45, "action": "('stop', 'stop')" }	{ "step": 23, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	3356a2438e3def7e0a947cf03b98229dede2ee2331ba17e4f21d865026d4d7a8
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	4	toy_maze_2d/train/batch_000000.jsonl	17	[ 13, 14 ]	16	[ "('move', 2)", "('move', 1)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 2)","vlm_output":"<think></think><answer>('move', 2)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[27,29],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"(...TRUNCATED)	{ "assistant_turn_index": 33, "action": "('stop', 'stop')" }	{ "step": 17, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	1ebbf679b652fa59f8a4c53f6b365cf0fedc505293829f7bd9883a00cc928b9d
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	5	toy_maze_2d/train/batch_000000.jsonl	17	[ 3, 5 ]	16	[ "('move', 3)", "('move', 2)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 3)","vlm_output":"<think></think><answer>('move', 3)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[7,11],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"t(...TRUNCATED)	{ "assistant_turn_index": 33, "action": "('stop', 'stop')" }	{ "step": 17, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	f36d5bb7996c1026fcf5b70c03f87058cf63320fec9ff0e8bee48d7672f80e21
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	6	toy_maze_2d/train/batch_000000.jsonl	15	[ 7, 11 ]	14	[ "('move', 0)", "('move', 1)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 0)","vlm_output":"<think></think><answer>('move', 0)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[15,23],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"(...TRUNCATED)	{ "assistant_turn_index": 29, "action": "('stop', 'stop')" }	{ "step": 15, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	ae1ce55586dd135544c0e061511bc3b004bd09aee12324a3c1b0de1ffbd9e65f
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	7	toy_maze_2d/train/batch_000000.jsonl	23	[ 3, 16 ]	22	[ "('move', 2)", "('move', 1)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 1)","vlm_output":"<think></think><answer>('move', 1)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[7,33],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"t(...TRUNCATED)	{ "assistant_turn_index": 45, "action": "('stop', 'stop')" }	{ "step": 23, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	afd116e7969ea0132b98be6a0a56998c3a3ea6f3fe97900a43cc690b16c13fda
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	8	toy_maze_2d/train/batch_000000.jsonl	15	[ 0, 9 ]	14	[ "('move', 1)", "('move', 2)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 1)","vlm_output":"<think></think><answer>('move', 1)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[1,19],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"t(...TRUNCATED)	{ "assistant_turn_index": 29, "action": "('stop', 'stop')" }	{ "step": 15, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	124eabca6c7b4c4d61cb8e806bbfdf99b7e326486014f060593a6149689a220d
toymaze_2d_visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_future_rollout_cot_v1	visgym_source_allstep_two_key_future_rollout_and_stop	toy_maze_2d	official_visgym_train	train	9	toy_maze_2d/train/batch_000000.jsonl	15	[ 5, 10 ]	14	[ "('move', 2)", "('move', 2)" ]	('stop', 'stop')	[{"role":"user","content":[{"type":"text","text":"You are navigating a 9x9 maze. The maze consists o(...TRUNCATED)	[{"step":0,"action":"('move', 1)","vlm_output":"<think></think><answer>('move', 1)</answer>","reward(...TRUNCATED)	{"kind":"hf_visgym_data_toy_maze_2d_train","source_repo":"VisGym/visgym_data","source_path":"toy_maz(...TRUNCATED)	{"assistant_turn_indices":[11,21],"generated_image_count":8,"image_encoding":"base64_jpeg","scope":"(...TRUNCATED)	{ "assistant_turn_index": 29, "action": "('stop', 'stop')" }	{ "step": 15, "reward": 1, "terminated": true, "truncated": false }	{"pipeline":"toymaze_2d_visgym_source_allstep_future_rollout_cot_v1","generated_at":"2026-05-09T01:0(...TRUNCATED)	5d9450b0cfb794162fdb80e5531b9805cbadbc55236b3a48a55abc3880aad98c

End of preview.

ToyMaze2D Official VisGym Source All-Step Future-Rollout Natural COT

Source dataset: https://huggingface.co/datasets/VisGym/visgym_data/tree/main/toy_maze_2d/train

This dataset preserves the official VisGym ToyMaze2D training trajectory prompts, actions, image_prev, image, image_next, generated future-rollout images, and source step budget. Each row is an all-step user/assistant conversation with two selected move steps containing four one-step future rollout images each. Only the final text item of each selected rollout assistant turn was rewritten to use the natural_paragraph style. The key rollout thinking paragraphs avoid numeric remaining-distance mentions.

Records: 99899 Skipped official source records: 101 Generated rollout images: 799192 Key template id: toymaze_allstep_key_rollout_natural_v2

Target Hub repo: https://huggingface.co/datasets/novastar112/toy_maze_2d_visgym_train_allstep_thinking_future_rollout_cot

Downloads last month: 12

Total file size:

3.94 GB