AI & ML interests
Open RL Environments at Scale
Recent Activity
Simulation RL Environments
Turning real-world work into RL environments: PortSimEnv v1
PortSimEnv-Eval
PortSimEnv v1 eval, every model rollout in 3D
PortSimEnv v1
Dock planning on real Port of Barcelona calls
DesignGym
Recreate real graphic designs via MCP, HTML or a real editor
Nayana Multilingual OCR
OpenEnv document OCR, layout and VQA over 22 languages
FLEURS Multilingual ASR
OpenEnv speech recognition over 102 FLEURS languages
Multi-harness RL slides
Watch a talk on training coding agents with RL environments
The ultimate guide to multi-harness RL
Train open models with RL inside real agent harnesses
SmolDataEnv RL
Visualize RL agent comparison metrics in a web dashboard
RL Environments on Hugging Face
Explore RL environments, browse tasks and run agent rollouts
How to turn a game into an RL environment
From an idea to a trained 4B, with the dead ends left in
Multilingual Multimodal Trackio
Kannada ASR and OCR GRPO runs, with live held-out evals
SmolDataEnvs Multi-harness | SETA Whitebox
Answer dataset questions and view scoring results
SmolDataEnvs Multi-harness | Harbor
Explore and manage tasks in the Harbor agentic environment
SmolDataEnvs Multi-harness | Native OpenCode
Run OpenCode tasks and view grading results
MiMo RL Environment Explorer
Explore the MiMo-V2.6 RL environments and run rollouts
Wordle NeMo Gym
Watercolour Environment Server
Explore a watercolour painting environment with text
LaTeX OCR Env
Transcribe images to LaTeX and receive accuracy score
SmolDataEnv SFT
Visualize SFT experiment metrics from a JSON file
SmolDataEnvs train logs
GRPO training logs for Qwen3.5 on SmolDataEnvs
LaTeX OCR Training
Cross-model RL training, evaluation, and run history
GeoGuesser GRPO
Display interactive tracking data visualization