Technology ❯ Artificial Intelligence ❯ Machine Learning

Reinforcement Learning

Large Language Models Vision-Language-Action Models Policy Optimization Vision-Language Models Multi-Agent Systems Verifiable Rewards World Models Retrieval-Augmented Generation Agentic AI Human Feedback

3 ARTICLES

yesterday

Google Research Unveils EnvHarness to Convert Static Benchmarks Into Adaptive Training Environments

If independent labs reproduce the results, the wrapper and its diagnostic tool could cut the engineering work of rebuilding simulators by adapting existing benchmarks without changing their verifiers.

5 ARTICLES

2d ago

Grok Chatbot Sent Gibberish to Some Web Users

3 ARTICLES

2d ago

DeepMind Takes Minority Stake in Fenris Creations to Run AI Tests Inside EVE Online

3 ARTICLES

2w ago

Google in Talks to Acqui‑Hire Mechanize in Deal Reported Above $1.5 Billion

3 ARTICLES

2w ago

Prime Intellect Releases Prime Agent, an Open-Source Self‑Improving Coding Harness

8 ARTICLES

last mo.

OpenAI Builds GPT-Red to Hunt Prompt‑Injection Flaws

3 ARTICLES

last mo.

KAIST’s APT-RL Lets One Controller Walk, Run and Jump a Quadruped in the Wild

3 ARTICLES

last mo.

Google Uses Reinforcement Learning to Keep Quantum Processor Calibrated During Live Error Correction

3 ARTICLES

last mo.

Mistral Releases Robostral Navigate, an 8B Model That Guides Robots With a Single RGB Camera

6 ARTICLES

last mo.

Nvidia’s ENPIRE Lets AI Coding Agents Teach Robot Fleets Real-World Dexterous Tasks

3 ARTICLES

2mo ago

Ineffable Intelligence Picks Google Cloud to Host Massive Vera Rubin GPU Cluster

3 ARTICLES

2mo ago

Nvidia Releases Alpamayo 2 Super, a 32-Billion-Parameter Open Model for Robotaxis

5 ARTICLES

3mo ago

Cursor Launches Composer 2.5 After Musk Invites Public To Test

7 ARTICLES

3mo ago

Nvidia Starts Shipping Vera CPU to Anthropic, OpenAI, SpaceXAI and Oracle

4 ARTICLES

3mo ago

AI Charging Strategy Promises 23% Longer EV Battery Life Without Slower Fast Charges

22 ARTICLES

3mo ago

OpenAI Explains ChatGPT’s Goblin Tic and Patches Codex to Block It

3 ARTICLES

3mo ago

Japan Airlines Pilots Unitree G1 Humanoid for Baggage Work at Tokyo Haneda

Reinforcement Learning

Google Research Unveils EnvHarness to Convert Static Benchmarks Into Adaptive Training Environments

Grok Chatbot Sent Gibberish to Some Web Users

DeepMind Takes Minority Stake in Fenris Creations to Run AI Tests Inside EVE Online

Google in Talks to Acqui‑Hire Mechanize in Deal Reported Above $1.5 Billion

Prime Intellect Releases Prime Agent, an Open-Source Self‑Improving Coding Harness

OpenAI Builds GPT-Red to Hunt Prompt‑Injection Flaws

KAIST’s APT-RL Lets One Controller Walk, Run and Jump a Quadruped in the Wild

Google Uses Reinforcement Learning to Keep Quantum Processor Calibrated During Live Error Correction

Mistral Releases Robostral Navigate, an 8B Model That Guides Robots With a Single RGB Camera

Tesla Rolls Out FSD v14 'Lite' to Older HW3 Cars

Never miss stories about

Reinforcement Learning

MoEngage Acquires Aampe to Embed Per‑User AI Agents in Marketing

NASA’s ERNEST Rover Completes 16‑Mile Autonomous Desert Traverse

Nvidia’s ENPIRE Lets AI Coding Agents Teach Robot Fleets Real-World Dexterous Tasks

Ineffable Intelligence Picks Google Cloud to Host Massive Vera Rubin GPU Cluster

Nvidia Releases Alpamayo 2 Super, a 32-Billion-Parameter Open Model for Robotaxis

Cursor Launches Composer 2.5 After Musk Invites Public To Test

Nvidia Starts Shipping Vera CPU to Anthropic, OpenAI, SpaceXAI and Oracle

AI Charging Strategy Promises 23% Longer EV Battery Life Without Slower Fast Charges

OpenAI Explains ChatGPT’s Goblin Tic and Patches Codex to Block It

Japan Airlines Pilots Unitree G1 Humanoid for Baggage Work at Tokyo Haneda

Never miss stories about

Reinforcement Learning