stable-baselines
DI-engine
Our great sponsors
stable-baselines | DI-engine | |
---|---|---|
10 | 3 | |
4,000 | 2,553 | |
- | 2.8% | |
0.0 | 8.7 | |
over 1 year ago | 4 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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.
stable-baselines
-
Distributed implementation tips
As underlined by gold-panda, you can give a try with multiprocessing. I once implemented a version based on what is done in stable_baselines v1 (https://github.com/hill-a/stable-baselines/blob/master/stable_baselines/common/vec_env/subproc_vec_env.py)
-
GAIL without actions?
Found relevant code at https://github.com/hill-a/stable-baselines + all code implementations here
-
Best framework to use if learning today
Depends what you wanna do. Universal answer would be https://stable-baselines.readthedocs.io/
-
weird mean reward graph
As you will see here it is recommended to augment this safety measure with target kl_divergence, that will ensure even smoother learning and enforce early stopping to prevent learning collapses.
-
Nvidia ISAAC gym/RL
Code for https://arxiv.org/abs/1707.06347 found: https://github.com/hill-a/stable-baselines
- Bounds for observation
-
Understanding multi agent learning in OpenAI gym and stable-baselines
I haven't read the code, but stable-baselines doesn't support multi-agent environments (https://github.com/hill-a/stable-baselines/issues/423), so I think they're trying to make learning multi-agent easier with Environment.train().
- Using Reinforment Learning to beat the first boss in Dark souls 3 with Proximal Policy Optimization
-
Reinforcement Learning Crash Course (Free)
- https://github.com/hill-a/stable-baselines (Tensorflow)
-
JAX Implementations of Actor-Critic Algorithms
- tf2 speed: https://github.com/hill-a/stable-baselines/issues/576#issuecomment-573331715
DI-engine
-
Anyone have experience with DI-Engine?
I posted a while back asking people what frameworks they were using for RL research. Recently i stumbled upon DI-Engine which looks promising! Actively maintained, with a diverse set of algorithms already implemented.
-
TransformerXL + PPO Baseline + MemoryGym
DI Engine
- Struggling with algorithm generality? Try DI engine; here is the solution
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
pytorch-a2c-ppo-acktr-gail - PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
tianshou - An elegant PyTorch deep reinforcement learning library.
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
Tic-Tac-Toe-Gym - This is the Tic-Tac-Toe game made with Python using the PyGame library and the Gym library to implement the AI with Reinforcement Learning
on-policy - This is the official implementation of Multi-Agent PPO (MAPPO).
gym
myosuite - MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.