rl-baselines-zoo
Minigrid
rl-baselines-zoo | Minigrid | |
---|---|---|
2 | 8 | |
1,106 | 2,008 | |
- | 0.4% | |
0.0 | 6.9 | |
over 1 year ago | 8 days ago | |
Python | Python | |
MIT License | 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.
rl-baselines-zoo
-
Agent trains great with PPO but terrible with SAC --> Advice for Hyperparameters
Take a look at these tuned sets of hyperparameters for various problems in PPO and SAC. The batch sizes are WAY smaller regardless of the problem. Your initial learning rate may also be too high.
-
How do I convert zoo / gym trained models to TensorFlow Lite or PyTorch TorchScript?
https://github.com/araffin/rl-baselines-zoo (TensorFlow based, using https://github.com/hill-a/stable-baselines)
Minigrid
- Environments that require long-term memory and reasoning
-
Best GridWorld environment?
If you want something as simple as possible, I'd go with MiniGrid, and if you want to have a richer world with more complex settings, then MiniHack.
-
Using FastAI to navigate matterport spaces?
This is a pretty hard domain to start with as someone "brand new" to AI. If you're interested in the vision aspect, I'd suggest you start by training a DNN for the CIFAR-10 task. There are plenty of tutorials out there. If you're more interested in the navigation aspect, you could start by training a Q-learning agent to solve some of the simpler problems in gym-minigrid.
-
How to train an agent in custom mini-grid environment using stable baselines3?
Hello guys I tried to build a custom environment using maxicymeb repo
-
What OpenAI Gym environments are your favourite for learning RL algorithms?
For learning and experimentation with RL algorithms, I suggest using a grid world implementation: observations are simple enough (most implementations have a one-hot layered observation) that you do not need deep conv layers to learn complex visual features. You can also make grid worlds as simple or as complex as you like by adding enemies, objects, key-door pairs, changing the size of the grid or decreasing observation radius, etc. There is a reason they are commonly used in research.
- RL environment for hard exploration (infinite) task
-
[R] Are there any paper about reinforcement learning solving mazes?
Take a look at: https://github.com/maximecb/gym-minigrid
What are some alternatives?
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
pytorch-blender - :sweat_drops: Seamless, distributed, real-time integration of Blender into PyTorch data pipelines
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
MinAtar
pybullet-gym - Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
gym-super-mario-bros - An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES
ma-gym - A collection of multi agent environments based on OpenAI gym.
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
marlgrid - Gridworld for MARL experiments
gym - A toolkit for developing and comparing reinforcement learning algorithms.
rlcard - Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.