Dobb·E: An open-source, general framework for learning household robotic manipulation
-
Updated
Oct 15, 2024 - G-code
#
behavior-cloning
Here are 110 public repositories matching this topic...
Official code repository of "VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video" @ NeurIPS 2025
-
Updated
Sep 21, 2026 - Python
RL based agent for browser-based multiplayer battle royale game «surviv.io»
python opencv machine-learning reinforcement-learning computer-vision deep-learning selenium pytorch behavior-cloning
-
Updated
Mar 9, 2022 - Jupyter Notebook
This repository contains the code for the CVPR 2020 paper "Exploring Data Aggregation in Policy Learning for Vision-based Urban Autonomous Driving"
dart dagger autonomous-driving imitation-learning online-learning behavior-cloning data-distribution cvpr2020
-
Updated
Sep 17, 2020 - Python
Machine learning robotics engineer preparation material.
reinforcement-learning computer-vision robotics transformers cnn rnn motion-capture slam robotics-control 3d-scanning diffusion behavior-cloning ml-system-design ml-system-diagrams
-
Updated
Mar 27, 2025 - HTML
MinBC - Minimal Behavior Cloning
-
Updated
Jul 5, 2026 - Python
Anchor-Align (arXiv:2607.13429): VLA finetuning that prevents behavior cloning from erasing pretrained VLM representations (catastrophic forgetting) and aligns language with actions. OOD generalization on a physical xArm7, LIBERO-PRO, LIBERO-Plus and CALVIN.
robotics pytorch imitation-learning calvin knowledge-distillation vla robot-learning generalization language-grounding catastrophic-forgetting behavior-cloning robot-manipulation embodied-ai libero ood-generalization foundation-models vision-language-model vision-language-action
-
Updated
Oct 24, 2026 - Python
Headless Warcraft III (Legacy TFT 1.29) under Wine for reinforcement learning: the real game stepped from Python, with PufferLib 5 training, behavior cloning and a training dashboard.
reinforcement-learning jass warcraft3 wine rts game-ai gymnasium ppo warcraft-iii behavior-cloning self-play pufferlib
-
Updated
Nov 12, 2026 - Python
Official implementation of "Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories" (ENAP, RSS 2026): neuro-symbolic imitation learning that learns task structure from demonstrations as a state machine.
state-machine formal-methods imitation-learning robot-learning behavior-cloning neuro-symbolic-learning automata-learning task-structure maniskill
-
Updated
Oct 21, 2026 - Python
stable-baselines with JAX & Haiku
reinforcement-learning imitation-learning diffusion haiku dataset-aggregation proximal-policy-optimization behavior-cloning jax soft-actor-critic dm-haiku decision-transformers
-
Updated
Jun 20, 2024 - Python
A minimal Vision-Language-Action model you can read: frozen CLIP + a tiny head on ManiSkill PickCube. LeRobot integration. Runs on a Mac, no GPU.
machine-learning robotics pytorch manipulation clip imitation-learning vla robot-learning behavior-cloning robot-manipulation embodied-ai vision-language-action lerobot maniskill
-
Updated
Jul 13, 2026 - Python
Game AI experimentation framework for imitation learning, computer vision, and automated dataset collection
electron reinforcement-learning computer-vision cpp pytorch yolo imitation-learning game-ai onnx behavior-cloning
-
Updated
Oct 21, 2026 - TypeScript
CAIL (IROS 2025): constraint-aware behavior cloning with privileged training-time safety supervision for autonomous racing, without an additional safety filter at deployment.
imitation-learning robot-learning behavior-cloning carla-simulator autonomous-racing safety-filter safe-learning
-
Updated
Sep 13, 2026 - Python
mAIjong 麥醬：台灣十六張麻將的多人線上對戰、AI 教練、RL 強化學習研究與競賽平台。支援即時多人房間、快速配對、斷線 AI 接手、39 種台型計分規則引擎、牌局重播與分析、AI 教練、情境／速度／防守練習、PWA、賽季排行榜與社群代理競技場；提供代理 SDK、Gymnasium／PettingZoo 多代理環境、合法動作遮罩、BC、Dueling DQN、PPO、MaskablePPO、CEM、自我對弈、配對評估及訓練實驗室。使用以下技術建置：FastAPI、WebSocket、Next.js、PixiJS、PyTorch、PostgreSQL、Redis、S3、Docker
reinforcement-learning game-engine websocket nextjs dqn pixijs gymnasium online-multiplayer ppo behavior-cloning self-play multi-agent-reinforcement-learning mahjong-ai fastapi pettingzoo stable-baselines3 agent-sdk taiwanese-mahjong
-
Updated
Nov 1, 2026 - Python
DRL agent for MicroRTS: U-Net + entity-Transformer (UECD) policy trained with modular PPO. Tops a 19-agent IEEE-CoG-style tournament at 96.67% WR and beats RAISocketAI in 65.7% of head-to-heads, on a 9.47 GPU-day budget. Master's thesis, UCLouvain 2026.
reinforcement-learning deep-reinforcement-learning pytorch transformer real-time-strategy masters-thesis proximal-policy-optimization behavior-cloning self-play reward-shaping microrts game-theoretic-evaluation
-
Updated
Sep 19, 2026 - Python
End-to-end deep RL for urban autonomous driving in CARLA — PPO + Behavior Cloning, a custom CNN perception policy, and ROS 2 integration.
reinforcement-learning computer-vision deep-learning robotics pytorch self-driving-car autonomous-driving imitation-learning ros2 ppo carla behavior-cloning stable-baselines3
-
Updated
Jun 7, 2026 - TeX
FFXIV CCG（Context Combat Generator）—— FFXIV 战斗场景的生成式决策模型：FFLogs 采集、行为克隆预训练、GRPO 后训练、ONNX 部署导出、模型表征分析与自回归回放
machine-learning reinforcement-learning deep-learning transformers pytorch game-ai final-fantasy-xiv ffxiv onnx fflogs behavior-cloning grpo
-
Updated
Oct 24, 2026 - Python
Mahjong AI workbench: our own offline + online RL pipeline (Mortal-architecture value network) aiming to beat Mortal v4 at riichi mahjong, every result measured by duplicate 1v3 matches. Plus a GPU-vectorized JAX line and from-scratch RL for Sichuan mahjong.
mahjong reinforcement-learning decision-model riichi behavior-cloning jax self-play mortal offline-rl
-
Updated
Nov 11, 2026 - Python
End-to-end self-driving AI in Forza using PyTorch, screen capture, telemetry, Grad-CAM, and virtual controller feedback.
python computer-vision deep-learning telemetry grad-cam cnn pytorch self-driving-car autonomous-driving imitation-learning game-ai end-to-end-learning virtual-controller explainable-ai behavior-cloning forza mobilenetv3 driving-simulator racing-simulator
-
Updated
Jun 1, 2026 - Python
Controlled study of how five demonstration failure modes affect behavior cloning, using 660 policy fits, two policy families, and transition-matched controls.
-
Updated
Sep 30, 2026 - Python
Add this topic to your repo
To associate your repository with the behavior-cloning topic, visit your repo's landing page and select "manage topics."