Miguel Alonso Jr.
@miguelalonsojr.bsky.social
Building generally intelligent agents - ML, RL, Robotics
@nfinite.ai
@nfinite.ai
So, after that long winded rant, I’m happy to share that I’m starting a new position as a Staff Research Engineer at Nfinite! Thank you to the amazing team at Nfinite for this wonderful opportunity.
April 1, 2025 at 5:04 PM
So, after that long winded rant, I’m happy to share that I’m starting a new position as a Staff Research Engineer at Nfinite! Thank you to the amazing team at Nfinite for this wonderful opportunity.
Playing around with Genesis and the SO-ARM100. Took some massaging, but IK pick works!
March 14, 2025 at 4:17 PM
Playing around with Genesis and the SO-ARM100. Took some massaging, but IK pick works!
Training the H1 to walk in 3 minutes. Genesis is crazy fast. Dang... Trained from scratch using PPO on a single RTX4090. genesis-world.readthedocs.io #reinforcementlearning #simulation
January 5, 2025 at 5:34 PM
Training the H1 to walk in 3 minutes. Genesis is crazy fast. Dang... Trained from scratch using PPO on a single RTX4090. genesis-world.readthedocs.io #reinforcementlearning #simulation
How the Perrinn 424 Agents "sees' it's environment... in addition to these exteroceptive sensors, the agent also has proprioceptive sensing of velocity, acceleration, etc etc, and some interoceptive sensing as well. #mlagents #unity #perrinn424project
December 7, 2024 at 12:26 PM
How the Perrinn 424 Agents "sees' it's environment... in addition to these exteroceptive sensors, the agent also has proprioceptive sensing of velocity, acceleration, etc etc, and some interoceptive sensing as well. #mlagents #unity #perrinn424project
Making progress... trained with ML-Agents Reinforcement Learning toolkit in Unity. #mlagents #unity #perrinn424project
December 6, 2024 at 3:06 AM
Making progress... trained with ML-Agents Reinforcement Learning toolkit in Unity. #mlagents #unity #perrinn424project
An oldie but goodie... thinking about resurrecting this one too... WDYT? Made with Unity, ML-Agents Reinforcement Learning toolkit... and lots of grit! A repro of this paper: proceedings.mlr.press/v164/rudin22...
November 25, 2024 at 7:10 PM
An oldie but goodie... thinking about resurrecting this one too... WDYT? Made with Unity, ML-Agents Reinforcement Learning toolkit... and lots of grit! A repro of this paper: proceedings.mlr.press/v164/rudin22...
Bringing back some fun work using ML-Agents to train reinforcement learning policies to drive the Perrinn 424 project electric car... stay tuned!
November 25, 2024 at 7:06 PM
Bringing back some fun work using ML-Agents to train reinforcement learning policies to drive the Perrinn 424 project electric car... stay tuned!