Trending

Show HN: ART – a new open-source RL framework for training agents

Mission Impossible: Managing AI Agents in the Real World

Watching 03 Model Sweat over a Paul Morphy Mate-in-2

Does RL Incentivize Reasoning in LLMs Beyond the Base Model?

Inner Loop Agents

Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents

Principles for Building One-Shot AI Agents

In Two Moves, AlphaGo and Lee Sedol Redefined the Future (2016)

Agency vs. Control vs. Reliability in Agent Design

A company gave 1,000 AI agents access to Minecraft — and they built a society

[R] Reinforcement Learning for Reasoning in Large Language Models with One Training Example

[D] Divergence in a NN, Reinforcement Learning

Fine tuning for Agentic Use Cases

[D] [P] Research Paper and Presentation about Multi-Agent Reinforcement Learning

We tried building actual agent-to-agent protocols. Here’s what’s actually working (and what’s not)

[D] A Bourgain-Embedding approach for abstract-board games?

Agents that can Start/Stop themselves

A Practical Guide to Building Agents

Xiaomi MiMo

Save item

MiMo-7B-RL

google-deepmind

Save item

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

microsoft

Save item

qlib

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.

DLR-RM

Save item

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.