Applied artificial intelligence research • Led by @0xreisearch
Joined November 2024
- Tweets718
- Following15
- Followers16.1K
- Likes2.3K
Pinned Tweet
Introducing Adapt-1 Machina: Learning Continuous Control Sequences
With Adapt-1 Machina, we explore how continuous sequences of machine controls can be learned through reinforcement learning, starting with coarse outcome feedback and without demonstrations or a critic.
Introducing CLP: coupled learning and planning from limited experience and delayed outcomes. Learning guides trials; planning and execution generate evidence.
We study a response to inevitable training-data scarcity, starting with adversarial decision-making and machine control.
The result is a retained skill: an acquired routine plus a learned correction for the starting observation. Both stay fixed during use, while commands vary with the start. The skill can execute without another search.
After acquisition and refinement, the frozen docking skill succeeded on 34/64 new starts through direct execution, or 52/64 with evaluation search. No learning took place during evaluation.
API details and examples: docs.reilabs.org
Adapt-1 Developer Docs v1.0 is live.
We’ve rebuilt the docs around getting started with Adapt-1 and understanding what you can build with it.
Quickstarts, API reference, mechanisms, traces, integration guidance, and use cases.
docs.reilabs.org/docs/neuroa…
Sign up and start building with Adapt-1:
app.reilabs.org/adapt-1
To understand what’s behind it:
Machina → reilabs.org/blog/adapt-1-mac…
Adaptive State → reilabs.org/blog/adaptive-st…
Adapt-1 Preview → reilabs.org/blog/introducing…
Discovery → reilabs.org/blog/emergence-t…
Machina brings continuous-control sequence learning to Adapt-1: learning from executed attempts, revising commands through feedback and retaining them for reuse.
Article: reilabs.org/blog/adapt-1-mac…
Try Adapt-1 Preview: app.reilabs.org/adapt-1