Results for "state evolution"
Reward only given upon task completion.
Learning action mapping directly from demonstrations.
Understanding objects exist when unseen.
AI giving legal advice without authorization.
Networks using convolution operations with weight sharing and locality, effective for images and signals.
Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.
Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.
Central system to store model versions, metadata, approvals, and deployment state.
Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.
GNN framework where nodes iteratively exchange and aggregate messages from neighbors.
Observing model inputs/outputs, latency, cost, and quality over time to catch regressions and drift.
Maintaining two environments for instant rollback.
Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.
System that independently pursues goals over time.
Interleaving reasoning and tool use.
Agent reasoning about future outcomes.
Agents communicate via shared state.
Control using real-time sensor feedback.
Control without feedback after execution begins.
Mathematical framework for controlling dynamic systems.
The physical system being controlled.
System returns to equilibrium after disturbance.
Finding control policies minimizing cumulative cost.
High-fidelity virtual model of a physical system.
Learning physical parameters from data.
RL without explicit dynamics model.
Hard constraints preventing unsafe actions.
Closed loop linking sensing and acting.
Mathematical guarantees of system behavior.
Modeling chemical systems computationally.