ReinforcementLearning.jl
procgen
ReinforcementLearning.jl | procgen | |
---|---|---|
2 | 3 | |
566 | 973 | |
1.6% | 0.7% | |
8.7 | 0.0 | |
15 days ago | 4 months ago | |
Julia | C++ | |
GNU General Public License v3.0 or later | 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.
ReinforcementLearning.jl
-
What framework would you recommend to build a Tetris game AI using reinforcement learning?
I has a look to Julia too. There are nice tools build by JuliaDynamics. I.e. Agents.jl for agent based modeling. It handles collisions. There is also a framework for reinforcement learning. Also for Genetic Algorithms. Then I found a set of libraries related to Geometry. But it seems to be a lot of work to put that together for my use case.
-
Any tutorial on how to create RL C++ environments?
And I know it's another language, but Julia has made significant strides in their RL packages and are pretty easy to integrate with Python
procgen
-
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.
What are some alternatives?
Agents.jl - Agent-based modeling framework in Julia
tiny-differentiable-simulator - Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.
NetLogo - turtles, patches, and links for kids, teachers, and scientists
open_spiel - OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
brax - Massively parallel rigidbody physics simulation on accelerator hardware.
RustyNEAT - Rust implementation of NEAT algorithm (HyperNEAT + ES-HyperNEAT + NoveltySearch + CTRNN + L-systems)
Numba - NumPy aware dynamic Python compiler using LLVM
julia - The Julia Programming Language
gym-super-mario-bros - An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES