GitHub / DistRL-lab / distrl-open
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DistRL-lab%2Fdistrl-open
PURL: pkg:github/DistRL-lab/distrl-open
Stars: 17
Forks: 0
Open issues: 0
License: apache-2.0
Language: Python
Size: 782 KB
Dependencies parsed at:
82
Created at: 11 months ago
Updated at: 6 months ago
Pushed at: 6 months ago
Last synced at: 6 months ago
Topics: agent, fine-tuning, llm-agent, llms, mllm, mobile, reinfrocement-learning
requirements.txt
pypi
- Farama-Notifications ==0.0.4
- Jinja2 ==3.1.2
- MarkupSafe ==2.1.3
- Pillow *
- PySocks *
- TatSu *
- accelerate *
- annotated-types ==0.6.0
- asyncssh *
- beautifulsoup4 *
- blis ==0.7.11
- brotlipy ==0.7.0
- catalogue ==2.0.10
- certifi *
- cffi *
- charset-normalizer *
- click ==8.1.7
- cloudpathlib ==0.16.0
- cloudpickle ==3.0.0
- confection ==0.1.3
- contourpy ==1.1.1
- cryptography *
- cycler ==0.12.1
- cymem ==2.0.8
- fonttools ==4.43.1
- google-generativeai *
- gradio *
- gym *
- gym-notices *
- gymnasium *
- hashids ==1.3.1
- hydra-core *
- jericho ==3.1.2
- jupyter *
- kiwisolver ==1.4.5
- langcodes ==3.3.0
- matplotlib ==3.8.1
- mementos ==1.3.1
- memory_profiler *
- more-itertools ==10.1.0
- murmurhash ==1.0.10
- networkx ==3.2.1
- numpy *
- openai *
- packaging ==23.2
- peft *
- pluggy *
- preshed ==3.0.9
- prompt-toolkit ==3.0.39
- pyOpenSSL *
- pycosat *
- pycparser *
- pydantic ==2.4.2
- pydantic_core ==2.10.1
- pyinstrument *
- pyparsing ==3.1.1
- python-dateutil ==2.8.2
- requests *
- ruamel.yaml *
- ruamel.yaml.clib *
- sentencepiece *
- six *
- smart-open ==6.4.0
- spacy ==3.7.2
- spacy-legacy ==3.0.12
- spacy-loggers ==1.0.5
- srsly ==2.4.8
- tenacity *
- termcolor *
- thinc ==8.2.1
- toolz *
- torch *
- tqdm *
- transformers ==4.37.2
- typer ==0.9.0
- typing_extensions ==4.8.0
- urllib3 *
- wandb *
- wasabi ==1.1.2
- wcwidth ==0.2.9
- weasel ==0.3.3
- zstandard *
setup.py
pypi