holodeck
dreamerv2
| holodeck | dreamerv2 | |
|---|---|---|
| 1 | 4 | |
| 564 | 853 | |
| 0.0% | - | |
| 0.0 | 0.0 | |
| about 2 years ago | over 1 year ago | |
| Python | Python | |
| MIT License | MIT License |
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.
holodeck
-
[P] Doing a clone of Rocket League for AI experiments. Trained an agent to air dribble the ball.
Tangentially related, but people interested in game engines for RL should check out Holodeck built on Unreal https://github.com/byu-pccl/holodeck
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
What are some alternatives?
MATLAB-Simulink-Challenge-Project-Hub - This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.
dreamerv3 - Mastering Diverse Domains through World Models
habitat-api - A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators. [Moved to: https://github.com/facebookresearch/habitat-lab]
dreamer - Dream to Control: Learning Behaviors by Latent Imagination
habitat-lab - A modular high-level library to train embodied AI agents across a variety of tasks and environments.
panda-gym - Set of robotic environments based on PyBullet physics engine and gymnasium.
ue4-docker - Windows and Linux containers for Unreal Engine 4
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
stable-baselines3-contrib - Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
ai2thor-rearrangement - 🔀 Visual Room Rearrangement
planet - Learning Latent Dynamics for Planning from Pixels