q-learning-algorithms
cleanrl
Our great sponsors
q-learning-algorithms | cleanrl | |
---|---|---|
1 | 41 | |
4 | 4,353 | |
- | - | |
0.0 | 6.7 | |
almost 3 years ago | about 1 month ago | |
Python | Python | |
- | GNU General Public License v3.0 or later |
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.
q-learning-algorithms
We haven't tracked posts mentioning q-learning-algorithms yet.
Tracking mentions began in Dec 2020.
cleanrl
-
[P] PettingZoo 1.24.0 has been released (including Stable-Baselines3 tutorials)
PettingZoo 1.24.0 is now live! This release includes Python 3.11 support, updated Chess and Hanabi environment versions, and many bugfixes, documentation updates and testing expansions. We are also very excited to announce 3 tutorials using Stable-Baselines3, and a full training script using CleanRL with TensorBoard and WandB.
- [P] 10x faster reinforcement learning hyperparameter optimization than SOTA - now with distributed training!
-
SB3 - NotImplementedError: Box([-1. -1. -8.], [1. 1. 8.], (3,), <class 'numpy.float32'>) observation space is not supported
I am trying to run cleanrl on the `Pendulum-v1` environment. I did that by going here and changing the default `env-id` to ` parser.add_argument("--env-id", type=str, default="Pendulum-v1",
-
[P] Robust Policy Optimization is now in CleanRL 🔥!
đź’ľcode: https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/rpo_continuous_action.py
Happy to share that CleanRL now has a new algorithm called Robust Policy Optimization — 5 lines of code change to PPO to get better performance in 57 out of 61 continuous action envs 🚀 (e.g., dm_control)
-
What's the best "Non-Black Box" framework for SOTA algorithms?
CleanRL is the gold standard for "approachable implementations" of the most popular RL algorithms, imo. Can't really beat single-file implementations in <= 200 lines of Python.
-
I could use some basic help
If you're interested in the theoretical foundations of RL, OpenAI's Spinning Up is an amazing resource that goes a bit easier on the math. For the practical side of things, I can't recommend Costa's CleanRL repo more. It has single file (~200ish lines of Python) implementations of most relevant RL algorithms, so it makes it really easy to grasp.
-
[P] 🔥 CleanRL has reached v1.0.0; Reworked documentation, JAX support, and more!
GitHub Release: https://github.com/vwxyzjn/cleanrl/releases/tag/v1.0.0
-
RL review
You can also reference the source code for some of the popular implementations from open source RL libraries like stablebaselines3, RLlib, CleanRL, or Dopamine. These can help you if you’re trying to compare your implementation to a “standard”.
-
What are sota hyperparameter optimization methods?
As far as I know CleanRL implements TPE. Also, I'm wondering if F-Race is considerable.
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
tianshou - An elegant PyTorch deep reinforcement learning library.
d3rlpy - An offline deep reinforcement learning library
reinforcement-learning-discord-wiki - The RL discord wiki
mbrl-lib - Library for Model Based RL
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
bomberland - Bomberland: a multi-agent AI competition based on Bomberman. This repository contains both starter / hello world kits + the engine source code
sample-factory - High throughput synchronous and asynchronous reinforcement learning
Deep-Reinforcement-Learning-Algorithms-with-PyTorch - PyTorch implementations of deep reinforcement learning algorithms and environments
wandb - 🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.
spinningup - An educational resource to help anyone learn deep reinforcement learning.
deep_rl_zoo - A collection of Deep Reinforcement Learning algorithms implemented with PyTorch to solve Atari games and classic control tasks like CartPole, LunarLander, and MountainCar.