agents-learning-sdk

Native reinforcement learning SDK for AI agents. An in-process learner optimizes a small, interpretable policy over discrete agent choices (understand intent and complete task by choosing the right outcome).

How it works

The SDK improves agents without LLM weight fine-tuning. There are no GPU fine-tune jobs and no opaque update cycles — just three pieces that run in your existing Python process:

  1. The policy is a softmax distribution over N discrete actions (e.g., "take action A", "take action B", "take action C"). It lives in Python and updates in milliseconds.

  2. Each episode is evaluated by three AI Evaluation evaluators — IntentResolutionEvaluator, TaskAdherenceEvaluator, and TaskCompletionEvaluator — whose scores are combined into a single scalar reward.

  3. A REINFORCE-with-baseline learner updates the policy logits directly from logged episodes. Updates are tiny gradient steps that run on local compute and persist through a pluggable store — in-memory or local files by default, with Azure Cosmos DB optional.

Every episode, reward, run, and deployment is captured by the configured store — in-memory or local files by default, or Azure Cosmos DB — giving you a complete lineage and audit trail of how the policy evolved over time.

Project links

Data verified by PyPI on
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for ctava-msft from gravatar.com ctava-msft

Credits

Author: Chris Tava

GitHub Statistics

Data verified by PyPI on 
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT License)

Requires

Python >=3.10

Provides Extra

dev cosmos nlp examples slm llm

Tags

reinforcement-learning ai-agents azure evaluation rlhf

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agents_learning_sdk-0.3.1.tar.gz (89.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agents_learning_sdk-0.3.1-py3-none-any.whl (98.4 kB view details)

Uploaded Python 3

File details

Details for the file agents_learning_sdk-0.3.1.tar.gz.

File metadata

  • Download URL: agents_learning_sdk-0.3.1.tar.gz
  • Upload date:
  • Size: 89.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for agents_learning_sdk-0.3.1.tar.gz
Algorithm Hash digest
SHA256 c21efce3636593b506c45f49ccdf72a5b47ba0a210b0e4b348020593e09b2f1b
MD5 74bc0458eaf8267eb57c5295aae80c23
BLAKE2b-256 c5fa493b378fc35383e880c465793682cc9208a268757ba51998f56c1dbb0980

See more details on using hashes here.

Provenance

The following attestation bundles were made for agents_learning_sdk-0.3.1.tar.gz:

Publisher: publish.yaml on microsoft/agents-learning-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file agents_learning_sdk-0.3.1-py3-none-any.whl.

File metadata

File hashes

Hashes for agents_learning_sdk-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1d5beec97ac4c38b5a5ff892e70596f9e06bd92f83057ce2b36c9ed5c9a77cf3
MD5 12b0a2adba098851e526fcf5ca1c3b1f
BLAKE2b-256 3aec58d96c385a5000c61f5672d3c43fcbc5e6336b00957aecce8f92d4676d08

See more details on using hashes here.

Provenance

The following attestation bundles were made for agents_learning_sdk-0.3.1-py3-none-any.whl:

Publisher: publish.yaml on microsoft/agents-learning-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page