PPO-PyTorch
cleanrl
| PPO-PyTorch | cleanrl | |
|---|---|---|
| 2 | 41 | |
| 1,493 | 4,529 | |
| - | - | |
| 2.8 | 6.3 | |
| 5 months ago | 21 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.
PPO-PyTorch
-
Where does the loss function for Policy Gradient come from?
It's just very convient implementation wise, in just a few lines you can get the "loss": (from https://github.com/nikhilbarhate99/PPO-PyTorch/blob/master/PPO.py)
-
A2C/PPO with continuous action space
In some methods, like the one here, the actor network has two heads, one for the mean and one for the variance. In other methods, like the one here, the network only outputs the mean, while the variance is pre-defined and is decaying throughout the training.
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.
-
PPO agent for "2048": help requested
Here's where the problem starts: after implementing a custom environment that follows the typical gymnasium interface, and use a slightly adjusted PPO implementation from CleanRL, I cannot get the agent to learn anything at all, even though this specific implementation seems to work just fine on basic gymnasium examples. I am hoping the RL community here can help me with some useful pointers.
- [P] 10x faster reinforcement learning hyperparameter optimization than SOTA - now with distributed training!
-
PPO ignores high rewards in deterministic sytem
Try out a standard implementation with some standard parameters from here: https://github.com/vwxyzjn/cleanrl/tree/master/cleanrl
-
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",
- Cartpole and mountain car
-
cleanrl gym issues
git clone https://github.com/vwxyzjn/cleanrl.git && cd cleanrl poetry install
-
Why is my Soft Actor Critic Algorithm not learning?
Can someone please help me debug my implementation of SAC. Please let me know if you have any questions. I tried comparing my work with CleanRL and caught a couple of errors. However, my implementation does diverge a lot from theirs as I wanted to test my understanding.
-
Model-based hierarchical reinforcement learning
Shameless self-plug: as far as implementation is concerned, I am working on a (hopefully) easier to understand Dreamer architecture under the CleanRL library, toward also re-implementing Director, Dreamer-v3, and and JAX variant for faster training.
-
[P] Robust Policy Optimization is now in CleanRL 🔥!
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 are some alternatives?
HandyRL - HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
l2rpn-baselines - L2RPN Baselines a repository to host baselines for l2rpn competitions.
tianshou - An elegant PyTorch deep reinforcement learning library.
Pytorch-PCGrad - Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"
d3rlpy - An offline deep reinforcement learning library
pytorch-accelerated - A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases, and capable of utilizing different hardware options with no code changes required. Docs: https://pytorch-accelerated.readthedocs.io/en/latest/
reinforcement-learning-discord-wiki - The RL discord wiki
nes-torch - Minimal PyTorch Library for Natural Evolution Strategies
mbrl-lib - Library for Model Based RL
autonomous-learning-library - A PyTorch library for building deep reinforcement learning agents.
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...