dreamerv2
dm_control
Our great sponsors
dreamerv2 | dm_control | |
---|---|---|
4 | 7 | |
853 | 3,540 | |
- | 2.5% | |
0.0 | 7.5 | |
over 1 year ago | 1 day 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.
dreamerv2
-
Sources of Actor Gradients
In fact, they found that just reinforce gradients work in DM control now too: Dreamerv2 GitHub (they just needed to turn off gradients through the action path - which I guess was being passed back with straight-through estimation? I'm actually having a difficult time telling how the gradient is different on the action vs policy.log_prob(action)).
-
PyDreamer: model-based RL written in PyTorch + integrations with DM Lab and MineRL environments
This is my implementation of Hafner et al. DreamerV2 algorithm. I found the PlaNet/Dreamer/DreamerV2 paper series to be some of the coolest RL research in recent years, showing convincingly that MBRL (model-based RL) does work and is competitive with model-free algorithms. And we all know that AGI will be model-based, right? :)
-
Any current state or the art libraries for training agents to play atari games?
Last I checked, for running off a single node, the state of the art was Dreamerv2 https://github.com/danijar/dreamerv2
- Google AI, DeepMind And The University of Toronto Introduce DreamerV2, The First Reinforcement Learning (RL) Agent That Outperforms Humans on The Atari Benchmark
dm_control
-
Shimmy 1.0: Gymnasium & PettingZoo bindings for popular external RL environments
This includes single-agent Gymnasium wrappers for DM Control, DM Lab, Behavior Suite, Arcade Learning Environment, OpenAI Gym V21 & V26. Multi-agent PettingZoo wrappers support DM Control Soccer, OpenSpiel and Melting Pot. For more information, read the release notes here:
Have you ever wanted to use dm-control with stable-baselines3? Within Reinforcement learning (RL), a number of APIs are used to implement environments, with limited ability to convert between them. This makes training agents across different APIs highly difficult, and has resulted in a fractured ecosystem.
-
Installing & Using MuJoCo 2.1.5 with OpenAi Gym
Deepmind Control Suite is a good alternative to Open AI Gym for continuous control tasks. It contains many of the environments present in Gym and also a few extra ones. Deepmind Control Suite also uses Mujoco. I found the installation to be straightforward. Check out https://github.com/deepmind/dm_control
-
Is there a way to get PPO controlled agents to move a little more gracefully?
Do you know if this is implemented in code anywhere? I've been digging around in DeepMind's dm_control for the past few hours and I haven't found it. I'm not sure what I'm looking for either.
-
[D] MuJoCo vs PyBullet? (esp. for custom environment)
If you're interested in using Mujoco, I'd suggest checking out the dm_control package for Python bindings rather than interfacing with C++ directly. I think one downside to Mujoco currently is that you cannot dynamically add objects, and the entire simulation is initialized and loaded according to the MJCF / XML file.
- How to use MuJoCo from Python3
-
Any beginner resources for RL in Robotics?
DeepMind's dm control: https://github.com/deepmind/dm_control
What are some alternatives?
dreamerv3 - Mastering Diverse Domains through World Models
gym - A toolkit for developing and comparing reinforcement learning algorithms.
dreamer - Dream to Control: Learning Behaviors by Latent Imagination
baselines - OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
panda-gym - Set of robotic environments based on PyBullet physics engine and gymnasium.
IsaacGymEnvs - Isaac Gym Reinforcement Learning Environments
stable-baselines3-contrib - Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
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).
planet - Learning Latent Dynamics for Planning from Pixels
mujoco-py - MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
orion - Asynchronous Distributed Hyperparameter Optimization.
Robotics Library (RL) - The Robotics Library (RL) is a self-contained C++ library for rigid body kinematics and dynamics, motion planning, and control.