Results for “gymnasium”

22 skills

stable-baselines3

Train reinforcement learning agents using PPO, SAC, DQN, TD3, DDPG, and A2C algorithms with a scikit-learn-like API. Supports custom Gymnasium environments, vectorized environments, callbacks, and model persistence.

30.2k · bundle

More results

Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level.

scaffold-exercises

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

glip-grounded-language-image-pre-training-arxiv-2112-03857v2

GLIP: Grounded Language-Image Pre-training

scaffold-exercises

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting, then commit with git.

gamification-framework

Implements gamification elements in educational content with points, badges, leaderboards, and quests

improved-baselines-with-visual-instruction-tuning-arxiv-2310

Improved Baselines with Visual Instruction Tuning

windags-curator

Post-execution skill crystallization and learning engine updates for WinDAGs. Runs after successful execution to update Thompson sampling parameters, track method quality, detect monster-barring, log near-miss events, and signal Kuhnian crises. Activate on "curator", "learning update", "skill crystallization", "Thompson sampling", "monster-barring", "near-miss", "Kuhnian crisis", "post-execution learning". NOT for pre-execution risk scanning (use windags-premortem), retrospective analysis (use windags-looking-back), or DAG construction (use windags-architect).

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

emu-generative-pretraining-in-multimodality-arxiv-2307-05222

Emu: Generative Pretraining in Multimodality

Design badge and achievement systems for learning. TRIGGERS - Use when user needs help with badge-system related tasks.

杰诺斯（少年漫）认知与表达框架（压缩蒸馏）：改造人认真、战损美学、师徒忠犬触发：一拳超人等。虚构

imagenet-21k-pretraining-for-the-masses-arxiv-2104-10972v4

ImageNet-21K Pretraining for the Masses

琦玉（少年漫）认知与表达框架（压缩蒸馏）：无敌无聊、一拳解构热血、超市券日常触发：一拳超人等。虚构

Manim CE animations: 3Blue1Brown math/algo videos.

gpu-aware-training-config

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

emu2-generative-multimodal-models-are-in-context-learners-ar

Emu2: Generative Multimodal Models are In-Context Learners

workout-plan-generator

Generates personalized workout plans with progressive overload, periodization, and exercise variations

svit-scaling-up-visual-instruction-tuning-arxiv-2307-04087v2

SVIT: Scaling up Visual Instruction Tuning

Manim CE animations: 3Blue1Brown math/algo videos.

label-noise-sgd-provably-prefers-flat-global-minimizers-arxi

Label Noise SGD Provably Prefers Flat Global Minimizers

vessel3d-frangi-bugfix

Frangi vesselness 3D filter: Ra formula correction, scikit-image deprecations, GPU VRAM guard