coltra-rl

A modular implementation of PPO, and soon hopefully other algorithms.

Downloads
796
Stars
26
coltra-rl - v0.1.5 Latest Release

Published by RedTachyon about 1 year ago

Added LSTM models

Library is still under heavy development, so everything's changing all the time

coltra-rl - Thesis version

Published by RedTachyon about 1 year ago

Freezing the code as of the (probably) last PhD paper. After this, I might start decoupling the RL code from the thesis-specific elements to make it more widely usable.

coltra-rl - Reward paper

Published by RedTachyon over 1 year ago

coltra-rl - MCMES

Published by RedTachyon about 2 years ago

Version of the code used for MCMES experiments

coltra-rl - Understanding RL Crowds

Published by RedTachyon about 2 years ago

This version of coltra has been used for most of the experiments in "Understanding Reinforcement Learned Crowds"

coltra-rl - Fixed optuna sweep

Published by RedTachyon over 2 years ago

coltra-rl - First optuna sweep

Published by RedTachyon over 2 years ago

coltra-rl - v0.1.0-smartnav

Published by RedTachyon almost 3 years ago

This is a frozen version of the repository to work with SmartNav and SmartHider.

Note that the API diverged a bit between the two projects. SmartHider includes a legacy mode to be compatible with that. By default, this repo works with non-legacy SmartHider. To support legacy/SmartNav, make sure to appropriately modify the METRICS list in train_smartnav.py.