policy-based

一些簡單的遊戲，用來驗證強化學習中使用動作遮罩的效果及影響

Implementation of a multiprocessing Proximal Policy Optimization (PPO) algorithm on the BidepalWalker OpenAI Gym environment.

🎫 🔍 Check if your commit messages are in correct format based on policy

KeypointJS Identity-First API Framework with Mandatory Authentication

Policy based Reinforcement Learning techniques with REINFORCE and Actor Critic, applied to OpenAI's gym environments.

This module looks at policy based methods of reinforcement learning, principally the drawbacks to value based methods like Q learning that motivate the use of policy gradients.

This repo implements the REINFORCE algorithm for solving the Cart Pole V1 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1.

A robust, process-independent file rotator for Pharo Smalltalk. It monitors files (e.g., logs), rotates them based on configurable policies (size, age), and archives them.. It was specifically designed for heterogeneous environments (e.g. Go-Logger & Pharo-Rotator) and uses file-based locks to reliably avoid conflicts..

Result - Simple monad solution based on C++17 and policy based design