MintPlayer.AI.ReinforcementLearning.Environments
0.7.0
dotnet add package MintPlayer.AI.ReinforcementLearning.Environments --version 0.7.0
NuGet\Install-Package MintPlayer.AI.ReinforcementLearning.Environments -Version 0.7.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="MintPlayer.AI.ReinforcementLearning.Environments" Version="0.7.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="MintPlayer.AI.ReinforcementLearning.Environments" Version="0.7.0" />
<PackageReference Include="MintPlayer.AI.ReinforcementLearning.Environments" />
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add MintPlayer.AI.ReinforcementLearning.Environments --version 0.7.0
The NuGet Team does not provide support for this client. Please contact its maintainers for support.
#r "nuget: MintPlayer.AI.ReinforcementLearning.Environments, 0.7.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
#:package MintPlayer.AI.ReinforcementLearning.Environments@0.7.0
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=MintPlayer.AI.ReinforcementLearning.Environments&version=0.7.0
#tool nuget:?package=MintPlayer.AI.ReinforcementLearning.Environments&version=0.7.0
The NuGet Team does not provide support for this client. Please contact its maintainers for support.
MintPlayer.AI.ReinforcementLearning.Environments
Ready-made environments for MintPlayer.AI.ReinforcementLearning — pure managed C#:
- CartPole-v1 — a faithful Gymnasium port, validated bit-for-bit against recorded golden trajectories. Double DQN solves it in seconds.
- GridWorld / FrozenLake — tabular classics with a value-iteration oracle.
- 2048 — full board mechanics + an afterstate TD(0) n-tuple learner that reaches the 2048 tile in ~84% of games after ~3 minutes of self-play.
- Rush Hour — 6×6 sliding-block puzzle with masked 32-action space, a BFS optimal
solver, a seeded puzzle generator, and an imitation-learning toolkit:
RushHourOraclelabels every reachable state of a configuration with its exact distance-to-goal,RushHourPolicyNettrains on those labels, andRushHourPolicySearchruns policy-guided A* — solving official expert boards (ThinkFun card 40: 81 moves) optimally in ~2,500 node expansions.
using MintPlayer.AI.ReinforcementLearning.Core.Random;
using MintPlayer.AI.ReinforcementLearning.Core.Training;
using MintPlayer.AI.ReinforcementLearning.Environments;
var env = new CartPoleEnv();
var result = DqnTrainer.Train(env, new DqnOptions { SolveThreshold = 475 }, new SeedSequence(42));
Console.WriteLine($"solved after {result.StepsTrained} steps, eval {result.FinalEvalReturn:F1}");
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.
-
net10.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.10)
- MintPlayer.AI.ReinforcementLearning.Core (>= 0.7.0)
- MintPlayer.SourceGenerators.Attributes (>= 10.20.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.