Engineering AI Agents

BOOK
COURSES
VIDEOS
ABOUT ME

Vision Language Action Agents

Vision Language Action Agents

Build agents that act while grounding language, immitate and are self-deployable with Sim2Real.

Author

Pantelis Monogioudis

VLA Agents

Categories

All (5)

Transformers and Self-Attention

For the explanation of decoder-based architectures such as those used by GPT, please see the repo https://github.com/pantelis/femtotransformers and the embedded comments…

Single-head self-attention

In the simple attention mechanism, the attention weights are computed deterministically from the input context. We call the combination of context-free embedding (eg…

Multi-head self-attention

Earlier we have seen examples with the token bear being in multiple grammatical patterns that also influence its meaning. For example, we have seen the subject-verb-object…

Elementary Imitation Learning

In imitation learning a simulation engine is used to create training datasets. A screenshot of the simulator for the first track is shown below:

No matching items

Edit this page
View source
Report an issue