procgen
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments (by openai)
RustyNEAT
Rust implementation of NEAT algorithm (HyperNEAT + ES-HyperNEAT + NoveltySearch + CTRNN + L-systems) (by aleksander-mendoza)
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
procgen
Posts with mentions or reviews of procgen.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-03-19.
-
Is there a single-task, multi-scene environment using continuous action spaces like gym-super-mario-bros?
Is there a single-task, multi-scene environment using continuous action spaces? Single-task and multi-scene envs are similar to gym-super-mario-bros and CoinRun in procgen .But they are all discrete action spaces. Thank you!!!!!
-
My AI projects don't seem to learn, even if I use an official Gym environment. (Python 3.7)
And now "bigfish" from the procgen Gym environments, tested on Stable Baselines 3. (No success)
-
Any tutorial on how to create RL C++ environments?
It's not exactly a tutorial, but OpenSpiel has C++ environments ported to Python that are relatively simple and easy to understand. Procgen would be a more complicated reference to check out as well.
RustyNEAT
Posts with mentions or reviews of RustyNEAT.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-10-05.
-
Any tutorial on how to create RL C++ environments?
If you want to really speed up your environment several orders of magnitude, you can implement it in cuda/vulkan /opencl. Here is an example of what I did in vulkan https://mobile.twitter.com/MendozaDrosik It allows me to stimulate thousands of agents in parallel. Works wonders especially if you want to use genetic algorithms. If you're interested, I might make python bindings to my minecraft environment. If you write in rust (like I do), then you can add python bindings very easily with PyO3. This is what I did here https://github.com/aleksander-mendoza/RustyNEAT/blob/main/rusty_neat_quick_guide.py (it's GPU accelerated implementation of NEAT algorithm)
- Would I be able to train basic deep RL models on the m1 MacBook Air?
What are some alternatives?
When comparing procgen and RustyNEAT you can also consider the following projects:
tiny-differentiable-simulator - Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.
brax - Massively parallel rigidbody physics simulation on accelerator hardware.
open_spiel - OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
ReinforcementLearning.jl - A reinforcement learning package for Julia
Numba - NumPy aware dynamic Python compiler using LLVM
gym-super-mario-bros - An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES
procgen vs tiny-differentiable-simulator
RustyNEAT vs brax
procgen vs open_spiel
RustyNEAT vs tiny-differentiable-simulator
procgen vs ReinforcementLearning.jl
RustyNEAT vs ReinforcementLearning.jl
procgen vs brax
RustyNEAT vs Numba
procgen vs Numba
RustyNEAT vs open_spiel
procgen vs gym-super-mario-bros