Agents tagged "reinforcement-learning"

33 results
reinforcement-learning ×
Data & Analysis

AgileRL

Streamlines reinforcement learning with RLOps: evolutionary hyperparameter optimization removes exhaustive tuning runs for up to 10x faster training.

★ 951 FS 71 Some gaps 1d ago Apache-2.0
Data & Analysis

Relax Omni-Modal RL Engine

An asynchronous distributed reinforcement-learning engine for post-training text, vision, and audio models.

★ 621 FS 64 Some gaps 6d ago Apache-2.0
Dev & Engineering

HUD

A platform for building RL environments and evals for AI agents — define an environment once, then evaluate and train any model on it.

★ 302 FS 63 Some gaps 4d ago MIT
Data & Analysis

MetaClaw

A local proxy that turns personal-agent conversations into skills, memory, and optional scheduled LoRA learning.

★ 3.5k FS 50 Major gaps 3mo ago MIT
Data & Analysis

MobileGym

A programmable mobile simulator for deterministic GUI-agent evaluation and online RL training.

★ 794 FS 50 Major gaps 26d ago Apache-2.0
Dev & Engineering

Agentic RL: The Most Detailed Intro

A hands-on learning hub for Agentic RL — foundations, runnable code, an experiment-visualization dashboard, and readings of frontier base-model papers.

★ 359 FS 50 Major gaps 1mo ago
Data & Analysis

Tongyi DeepResearch

An open model and inference system for long-horizon web research, evidence gathering, and research question answering.

★ 20k FS 49 Major gaps 6mo ago Apache-2.0
Dev & Engineering

AWorld Agent Harness

Turn domain expertise into multi-agent workflows that build, evaluate, and iteratively improve concrete outputs.

★ 1.2k FS 48 Major gaps 4d ago MIT
Data & Analysis ✓ Microsoft · Official

MARO Resource Optimization Platform

Simulate and optimize real-world resource decisions with reinforcement learning and distributed components.

★ 925 FS 44 Major gaps 2y ago MIT
Dev & Engineering ✓ Microsoft · Official

Memora Agent Memory

A structured memory layer that stores rich agent history and retrieves it through abstractions and semantic cues.

★ 250 FS 44 Major gaps 3mo ago MIT
Dev & Engineering

IR-SIM: Lightweight Robot Simulator

A Python-based lightweight simulator for navigation, control, and learning, configured via simple YAML files.

★ 1.1k FS 43 Major gaps 5d ago MIT
Dev & Engineering

skrl: Modular Reinforcement Learning Library

A highly modular and readable RL library implemented in PyTorch, JAX, and NVIDIA Warp.

★ 1.1k FS 43 Major gaps 9d ago MIT
Automation & Ops

gym-pybullet-drones: Quadcopter RL Environment

PyBullet-based Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control.

★ 2.1k FS 42 Major gaps 17d ago MIT
Data & Analysis ✓ Microsoft · Official

Agent Lightning

Capture agent trajectories and train improved prompts or policy resources for existing AI agents.

★ 18k FS 40 Major gaps 6d ago MIT
Dev & Engineering

MARTI: Multi-Agent Reinforced Training & Inference for LLMs

Train LLM-based multi-agent systems with reinforcement learning and tree-search-augmented reasoning across debate, chain-of-agents, and mixture-of-agents workflows.

★ 560 FS 36 Major gaps 1mo ago MIT
Data & Analysis

RLinf RL Infrastructure

Scalable reinforcement-learning infrastructure for embodied robotics and agentic AI training.

★ 5.3k FS 35 Major gaps 4d ago Apache-2.0
Data & Analysis

ART Agent Reinforcement Trainer

Train multi-step agents from real task experience with GRPO.

★ 11k FS 34 Major gaps today Apache-2.0
Dev & Engineering

AI Engineering from Scratch

A free, open-source curriculum of 503 lessons across 20 phases, teaching you to build AI end-to-end from math to agents.

★ 56k FS 33 Major gaps today MIT
Dev & Engineering

ChatArena

A Python framework for building and running multi-agent language-game experiments with LLM players.

★ 1.6k FS 32 Major gaps 1y ago Apache-2.0
Data & Analysis

veRL Agent Training

Multi-turn reinforcement learning training for long-horizon LLM and vision-language agents.

★ 2.3k FS 32 Major gaps 3mo ago Apache-2.0
Data & Analysis

AgentFlow

Train an in-system planner with Flow-GRPO for more reliable multi-tool, long-horizon reasoning.

★ 2k FS 31 Major gaps 7mo ago MIT
Dev & Engineering

Hands-On Modern RL

A practice-first reinforcement learning course from CartPole to LLM post-training and agentic systems.

★ 4.4k FS 30 Major gaps 20d ago NOASSERTION
Automation & Ops

Mobile-Agent: A Family of Powerful GUI Agents

A multi-platform GUI agent family by Alibaba's Tongyi Lab, automating mobile, desktop, and web tasks via multimodal models.

★ 9.2k FS 29 Major gaps 2mo ago MIT
Dev & Engineering

AgentsMeetRL — Awesome List of Agentic Reinforcement Learning

A curated, categorized collection of open-source RL-training projects for LLM agents, with technical details and an interactive dashboard.

★ 1.8k FS 29 Major gaps 8d ago