Deep Reinforcement Learning

Good News for Programmers! The Open Source Multi-SWE-bench by Doubao Team Tackles Code Bugs and Assesses Model Performance!

by
Good News for Programmers! The Open Source Multi-SWE-bench by Doubao Team Tackles Code Bugs and Assesses Model Performance!

Programmers, are you fighting bugs every day? Good news is here! Recently, the Doubao Team from ByteDance has made a significant move by open-sourcing a tool called Multi-SWE-bench. This is not just an ordinary tool; it is specifically designed to test the “automatic bug-fixing” capabilities of large models, and it supports multiple programming languages! Now … Read more

Affordable AI Robot Training: Google Brain & Berkeley Launch Low-Cost Robot Training Platform ROBEL

by
Affordable AI Robot Training: Google Brain & Berkeley Launch Low-Cost Robot Training Platform ROBEL

New Intelligence Report Source: GoogleAI Editors: Xiao Qin, Da Ming [New Intelligence Overview] Making robot research accessible to the public. Researchers from the University of California, Berkeley, and Google Brain have jointly developed the low-cost robot learning platform ROBEL, which supports the expansion of robot experiments and reinforcement learning, while ensuring robustness, flexibility, and reproducibility. … Read more

Multi-SWE-bench: The First Multilingual Code Repair Benchmark Open Source

by
Multi-SWE-bench: The First Multilingual Code Repair Benchmark Open Source

The ByteDance Doubao large model team has officially open-sourced the first multilingual SWE dataset – Multi-SWE-bench, which can be used to evaluate and enhance the “automatic bug fixing” capabilities of large models.Building on SWE-bench, Multi-SWE-bench covers seven mainstream programming languages beyond Python for the first time, making it a truly comprehensive benchmark for “full-stack engineering” … Read more

Google Researchers Propose Multi-Game Decision Transformers for Generalist AI Exploration

by
Google Researchers Propose Multi-Game Decision Transformers for Generalist AI Exploration

One of the long-term goals of artificial intelligence is to train a “generalist” model that can simultaneously solve various types of tasks, acting as a versatile general model. Currently, in the field of AI, the most rapid advancements are seen in subfields such as computer vision, natural language processing, and their intersections. One of the … Read more

Learn to Assemble Circuit Boards in 20 Minutes! Open Source SERL Framework Achieves 100% Success Rate with Three Times the Speed of Humans

by
Learn to Assemble Circuit Boards in 20 Minutes! Open Source SERL Framework Achieves 100% Success Rate with Three Times the Speed of Humans

Machine Heart ColumnMachine Heart Editorial Team Now, robots have learned to perform precision control tasks in factories. In recent years, significant progress has been made in the field of robotic reinforcement learning technologies, such as quadrupedal walking, grasping, and dexterous manipulation. However, most of these advancements remain limited to laboratory demonstrations. The widespread application of … Read more

Research on Resource Allocation for Dynamic Spectrum Access in Cognitive Radio Networks Based on Reinforcement Learning (Q-Learning)

by
Research on Resource Allocation for Dynamic Spectrum Access in Cognitive Radio Networks Based on Reinforcement Learning (Q-Learning)

Gift to Readers Conducting research involves a profound system of thought, requiring researchers to be logical, meticulous, and earnest. However, effort alone is not enough; leveraging resources is often more important. Additionally, one must have innovative and inspirational points of view. It is recommended that readers browse through the content in order to avoid suddenly … Read more

The World’s First! Humanoid Robot Achieves New Breakthrough!

by
The World's First! Humanoid Robot Achieves New Breakthrough!

Walking, running, jumping… the humanoid robot has achieved a new breakthrough, now capable of autonomously standing up! Recently, the Shanghai Artificial Intelligence Laboratory released the “world’s first humanoid robot autonomous standing control algorithm,” allowing the robot to stand up autonomously and steadily on various terrains and in different postures. How is this achieved? Let’s take … Read more

Academic Sharing | The Development History of AI Agents: From RL-Driven to Large Model-Driven

by
Academic Sharing | The Development History of AI Agents: From RL-Driven to Large Model-Driven

Reprinted from AI Technology ReviewInsights into the replication of Manus from cutting-edge research on agents. The emergence of Manus has pushed agents to the forefront of the current AI landscape, making this previously somewhat abstract concept tangible. However, there is no shortage of controversy in the industry regarding Manus, with critics arguing that it lacks … Read more