IEEE

Aligning Crowd-Sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models

Abstract: This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, ...
GitHub

PeRL: Permutation-Enhanced Reinforcement Learning

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, PeRL addresses a critical limitation in current multimodal reinforcement learning: ...
IEEE

Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations

Abstract: Multi-task multi-agent reinforcement learning (MT-MARL) is capable of leveraging useful knowledge across multiple related tasks to improve performance on any single task. While recent ...
Microsoft

Agent Lightning: Adding reinforcement learning to AI agents without code rewrites

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks ...
GitHub

gymnasium-robotics

Autonomous Rocket Landing with Deep Reinforcement Learning (Deep Q-Learning (DQN)) simulation in a custom Gymnasium environment inspired by SpaceX Falcon 9.