2 results found Sort:

EdanToledo
Stoix EdanToledo
26
252
apache-2.0
7
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
jax sarl anakin sebulba pure-jax research end-to-end single-agent single-agent-systems reinforcement-learning deep-reinforcement-learning reinforcement-learning-algorithms distributed-reinforcement-learning single-agent-reinforcement-learning
Created 2024-02-16
354 commits to main branch, last one 17 days ago
instadeepai
sebulba instadeepai
3
50
apache-2.0
5
🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
ai hpc jax ppo tpu sebulba podracer deep-learning machine-learning reinforcement-learning
Created 2023-09-04
3 commits to main branch, last one about a year ago