Cupertino, USA

Aleksei Petrenko

Expert
@alex-petrenko

Research Scientist at Apple. CS PhD, USC 2023. Interests: Deep Reinforcement Learning, Simulation, Optimization, Robotics, LLMs.

alex-petrenko.github.io/

sample-factory. High throughput synchronous and asynchronous reinforcement learning

1k

megaverse. High-throughput simulation platform for Artificial Intelligence reseach

229

faster-fifo. Faster alternative to Python's multiprocessing.Queue (IPC FIFO queue)

210

4dvideo. Capturing volumetric videos with Google Tango, RealSense R200 and Delaunay triangulation

43

curious-rl. Curiosity-driven Exploration by Self-supervised Prediction

24

signal-slot. Qt-like event loops, signals and slots for communication across threads and processes in Python

14

microtbs-rl. Training reinforcement learning agents to beat a simple turn-based strategy game

9

udacity-deep-learning. Python code written along the course.

4

quad-swarm-rl. Reinforcement learning for quadrotor swarms

3

landmark-exploration. Attempt to develop a new RL algorithm for hard exploration problems

3

seed_rl. SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

2

animations. Manim animations for various projects

2

snake-rl. Monte-Carlo rollout into the future predicted by DNN

2

ViZDoom. Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode:

2

vizdoomgym. Vizdoom wrapper for OpenAI gym

1

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

1

alex-petrenko.github.io. Personal website

1

tf-reinforce. Tensorflow implementation of the REINFORCE policy gradient algorithm

1

useful-stuff-i-always-forget. Miscellaneous stuff

1
19
Apply