Reinforcementlearning

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Pneumetron

Jul 20

Decoding the Link Between Pretraining and Reinforcement Learning

#airesearch #largelanguagemodels #reinforcementlearning #machinelearning

3 min read

Pneumetron

Jul 20

Muon Optimizer Boosts Agentic Reinforcement Learning Performance

#reinforcementlearning #muon #optimizer #agenticai

3 min read

Shoaibali Mir

Jul 18

The ~+9.4% You Can't Afford to Verify: Evaluating SDAR (and the FinOps of Trying)

#aws #machinelearning #mlops #reinforcementlearning

6 min read

Pneumetron

Jul 17

Length Penalties in LLMs: Shorter Chains of Thought, Hidden Influences

#llm #chainofthought #reinforcementlearning #interpretability

3 min read

Reno Lu

Jul 16

Agent Apprenticeship turns finished agent tasks into reusable experience

#aiagents #posttraining #agenttraces #reinforcementlearning

3 min read

Breach Protocol

Jul 1

AI Agents Are Learning to Build the Worlds They Train In

#aiagents #worldmodels #reinforcementlearning #alibaba

4 min read

Breach Protocol

Jul 2

Why teaching AI agents to use tools keeps blowing up in training

#reinforcementlearning #agents #tooluse #training

3 min read

Fazil Hasanov

Jun 19

Building a Self-Optimizing Python Trading Bot with Reinforcement Learning and Binance API

#python #trading #reinforcementlearning #binance

4 min read

Shoaibali Mir

Jun 14

The Whole Paper Fits in One Sigmoid: Implementing the SDAR Gate

#machinelearning #reinforcementlearning #python #aws

5 min read

Shoaibali Mir

Jun 6

Four Models in One Training Loop: Architecting SDAR on AWS (Before Renting a Single GPU)

#aws #machinelearning #reinforcementlearning #mlops

5 min read

SimTooReal

Jun 6

How to Add Live Telemetry and Failure Diagnosis to Isaac Lab, MuJoCo, or Gazebo Training in Under 5 Minutes

#ai #robotics #mujoco #reinforcementlearning

4 min read

Robosynx

May 30

Why robotics RL training pipelines fail at scale

#robotics #machinelearning #reinforcementlearning #simulation

4 min read

Jangwook Kim

May 27

ARTIST: RL-Powered Tool Use for LLM Agents Explained

#reinforcementlearning #llmagents #tooluse #agenticai

9 min read

Berkan Sesen

May 11

Q-Learning for Games: Teaching an Agent Tic-Tac-Toe Through Self-Play

#reinforcementlearning #gametheory

14 min read

Shoaibali Mir

May 31

Your RL Agent Failed a 12-Step Task. Which Step Was Wrong? (The Supervision Problem in Agentic RL)

#machinelearning #reinforcementlearning #llm #aws

5 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.