rmst/rlrd
PyTorch implementation of our paper Reinforcement Learning with Random Delays (ICLR 2020)
This project helps machine learning researchers and reinforcement learning practitioners evaluate and develop agents for environments where observations and actions are not instantaneous. It takes in a reinforcement learning environment definition and desired delay parameters, outputting performance metrics for agents trained under those conditions. It's designed for those pushing the boundaries of reinforcement learning in real-world systems with inherent delays.
No commits in the last 6 months.
Use this if you are a reinforcement learning researcher or practitioner needing to specifically study and implement algorithms that can handle random or fixed delays in observations and actions within simulated environments.
Not ideal if you are looking for a pre-optimized, production-ready solution for standard reinforcement learning tasks without a specific focus on time delays, as the current implementation prioritizes research and is not yet optimized for speed.
Stars
42
Forks
11
Language
Python
License
MIT
Category
Last pushed
May 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rmst/rlrd"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild