dreamerv2
dreamerv3
Our great sponsors
dreamerv2 | dreamerv3 | |
---|---|---|
4 | 3 | |
853 | 1,025 | |
- | - | |
0.0 | 1.9 | |
over 1 year ago | 8 days 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.
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
dreamerv3
- It would be cool if there was a machine learning Nes Emulator, that the ai could learn to play automatically and you just run it on your pc till it finds the optimum root.
- Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
- [R] [N] Mastering Diverse Domains through World Models - DreamerV3 - Deepmind 2023 - First algorithm to collect diamonds in Minecraft from scratch without human data or curricula! Now with github links!
What are some alternatives?
dreamer - Dream to Control: Learning Behaviors by Latent Imagination
daydreamer - DayDreamer: World Models for Physical Robot Learning
panda-gym - Set of robotic environments based on PyBullet physics engine and gymnasium.
crafter - Benchmarking the Spectrum of Agent Capabilities
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
iris - Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
stable-baselines3-contrib - Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
Datapack-Converter - Convert Minecraft command block chains to a datapack!
planet - Learning Latent Dynamics for Planning from Pixels
orion - Asynchronous Distributed Hyperparameter Optimization.
pydreamer - PyTorch implementation of DreamerV2 model-based RL algorithm
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)