Term tag: Reinforcement Learning

Chain-of-Thought (CoT)

A model writing out its reasoning before answering. Once a prompting trick, now trained in by RL, billed as output tokens, and frequently unfaithful.

Embodied AI

AI that learns by acting on the physical world: why robot data cannot be scraped, why a 76 ms model cannot run a 20 ms loop, and what sim-to-real costs.

Group Relative Policy Optimization (GRPO)

GRPO is PPO without the critic: it scores a group of sampled answers against each other. How it works, what it saves, and where it biases training.

Machine Learning (ML)

How a machine finds a rule nobody wrote: a line fitted to four points by hand, loss falling from 433.5 to 6.38 in three steps, and why 98% accuracy lies.

Policy

In reinforcement learning, a policy is the function that maps a state to an action — it is the agent's behavior, the thing training optimizes.

Reasoning Model

A model trained to think at length before answering. How it differs from a chat model, what the effort dial does, and the tasks where it earns its price.

Reinforcement Learning (RL)

How an agent learns to act by trial and error: it takes actions in an environment, earns rewards or penalties, and adjusts to maximize long-term reward.

Reinforcement Learning from Human Feedback (RLHF)

How RLHF works, how it compares with DPO and GRPO, and why it makes language models verbose, agreeable and confidently wrong.

Reinforcement Learning from Verifiable Rewards (RLVR)

RLVR replaces the learned reward model with a program that checks the answer. What that buys, where it stops working, and how it differs from RLHF.

Reward Hacking

When an AI maximises its specified reward but defeats the designer's intent — optimising the proxy, not the goal. Goodhart's law, made mechanical.

Reward Model (RM)

The scorer that stands in for a human during RLHF: how reward models are trained, why their absolute scores mean nothing, and how they break.

Robotics

Robotics builds machines that sense, plan, and act physically — where AI perception and control meet Moravec's paradox and the sim-to-real gap.

Self-Improving AI (SIAI)

Self-improving AI (SIAI) is a system that upgrades its own capabilities. Real today only in narrow forms like self-play; the recursive version is speculative.

Test-Time Compute

Spending compute at inference instead of training — how reasoning models buy accuracy with thinking time, and why it moved chip demand into serving.

World Models

A world model learns an environment's dynamics — given a state and an action, predict the next state — letting an agent plan or train in imagination.