DI-sheep
phillip
| DI-sheep | phillip | |
|---|---|---|
| 1 | 2 | |
| 362 | 539 | |
| 0.0% | - | |
| 10.0 | 0.0 | |
| about 1 year ago | over 1 year ago | |
| Python | Python | |
| Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
DI-sheep
phillip
-
[P] Imitation Learning (+RL) in Super Smash Bros Melee for Humanlike Agents
Project Nabla is an AI trained with deep neural networks using behavioral cloning and deep reinforcement learning self-play, similar to AlphaStar. It is enabled by the recent launch of a suite of software tools for the game known as "Slippi" which allow for us to save human replays. We train on a subset of ~100k tournament games. It is similar to the older Phillip project, which did not have the benefit of Slippi when it was created (and doesn't use any human replays).
-
Imma write a machine learning program and let it run for a month
Could take a look at this https://github.com/vladfi1/phillip
What are some alternatives?
habitat-api - A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators. [Moved to: https://github.com/facebookresearch/habitat-lab]
PyGame-Learning-Environment - PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
auction-app - A simple auction app built with React and Django.
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
habitat-lab - A modular high-level library to train embodied AI agents across a variety of tasks and environments.
deepdrive - Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving