rajcscw/nlp-gym

NLPGym - A toolkit to develop RL agents to solve NLP tasks.

nlp-gym's Issues

Generic Flair MultiLabelPool class

Are you asking pool request? I would like to help maintain the repo if you are open to it. I think this project is super cool and relevant to the research that I do. Making a generic Flair MultiLabelPool class would give access to all the sequence label datasets available in the flair repo.

HEAD request failed for url https://flair.informatik.hu-berlin.de/resources/embeddings/token/en-fasttext-news-300d-1M.vectors.npy with status code 503.

File "/home/neeson/DistributedES-master/config.py", line 14, in __init__
    env = QAEnv()
  File "/home/neeson/anaconda3/envs/es/lib/python3.7/site-packages/nlp_gym/envs/question_answering/env.py", line 43, in __init__
    observation_featurizer = InformedFeaturizer() if observation_featurizer is None else observation_featurizer
  File "/home/neeson/anaconda3/envs/es/lib/python3.7/site-packages/nlp_gym/envs/question_answering/featurizer.py", line 12, in __init__
    self.doc_embeddings = DocumentPoolEmbeddings([WordEmbeddings("en")])
  File "/home/neeson/anaconda3/envs/es/lib/python3.7/site-packages/flair/embeddings/token.py", line 170, in __init__
    cached_path(f"{hu_path}/en-fasttext-news-300d-1M.vectors.npy", cache_dir=cache_dir)
  File "/home/neeson/anaconda3/envs/es/lib/python3.7/site-packages/flair/file_utils.py", line 91, in cached_path
    return get_from_cache(url_or_filename, dataset_cache)
  File "/home/neeson/anaconda3/envs/es/lib/python3.7/site-packages/flair/file_utils.py", line 220, in get_from_cache
    f"HEAD request failed for url {url} with status code {response.status_code}."
OSError: HEAD request failed for url https://flair.informatik.hu-berlin.de/resources/embeddings/token/en-fasttext-news-300d-1M.vectors.npy with status code 503.

Excuse me, can you tell me why this happened?

Not getting installed with Python 3.10

Hi, I am trying install this package in Python 3.10 and it's throwing error.

running build_ext /bin/sh: 1: pkg-config: not found mkdir: cannot create directory ‘bundled’: File exists fatal: destination path 'sentencepiece' already exists and is not an empty directory. fatal: destination path 'sentencepiece' already exists and is not an empty directory. mkdir: cannot create directory ‘build’: File exists ./build_bundled.sh: 15: cmake: not found make: *** No targets specified and no makefile found. Stop. make: *** No rule to make target 'install'. Stop. env: ‘pkg-config’: No such file or directory Failed to find sentencepiece pkg-config

Please help me fix this. I don't want to downgrade my Python version.

multiprocess training and training details

How can i use multiprocess training? Can i use stable-baselines‘ multiprocessing interface？
And I also wonder training details to repeat the results of squence tagging. I run the script, and didn't get same good performance.
Thanks a lot.

Feature Request: update from gym to gymnasium

Hi, this repository is currently listed in the gymnasium third party environments but we are cleaning the list up to only include maintained gymnasium-compatible repositories.

Would it be possible for it to be upgraded from gym to gymnasium? Gymnasium is the maintained version of openai gym and is compatible with current RL training libraries (rllib and tianshou have already migrated, and stable-baselines3 will soon).

For information about upgrading and compatibility, see migration guide and gym compatibility. The main difference is the API has switched to returning truncated and terminated, rather than done, in order to give more information and mitigate edge case issues.