Toy MuJoCo + Box2d envs in OpenAI Gym are moving to #brax! 100x GPU/TPU speedup + purely pythonic + jax/pytorch-enabled ready to be unleashed! An exciting news for #brax #braxlines #jax teams. Also check out #composer, where I am adding more demos github.com/openai/gym/iss…
#braxlines:
#composer: github.com/google/brax/tr…
arxiv: arxiv.org/abs/2110.04686
#brax still cannot (and probably won't ever) match the full specs with mujoco/pybullet. But esp with open-sourcing plans of mujoco, excited to see where could be synergies.
https://twitter.com/shaneguML/status/1438696633437286400?s=20
#composer: github.com/google/brax/tr…
arxiv: arxiv.org/abs/2110.04686
#brax still cannot (and probably won't ever) match the full specs with mujoco/pybullet. But esp with open-sourcing plans of mujoco, excited to see where could be synergies.
Good to see a lot of large-scale, algorithmic deep RL researchers are aligned: "I personally believe that hardware accelerator support is more important, hence choosing Brax."
I believe hardware-accelerated sims (#brax, IsaacGym etc) are *finally* the MNIST moment for deep RL in control: something non-trivial (*not* cartpoles) can be trained within few minutes. Exciting times ahead for algorithmic researchers + scaling/generalization researchers.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
