Open Source Reinforcement Learning Algorithms - Page 3

This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA. The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms. Pac-Man", L.A.M. Bom (2012).

Multi-Agent Orchestrator is an AI coordination framework that enables multiple intelligent agents to work together to complete complex, multi-step workflows.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. Games are represented as procedural extensive-form games, with some natural extensions. The core API and games are implemented in C++ and exposed to Python. Algorithms and tools are written both in C++ and Python. To try OpenSpiel in Google Colaboratory, please refer to open_spiel/colabs subdirectory.

Using reinforcement learning in neural network for learning othello

PIQLE is a Platform Implementing Q-LEarning (and other Reinforcement Learning) algorithms in JAVA. Version 2 is a major refactoring. The core data structures and algorithms are in piqle-coreVersion2. Examples are in piqle-examplesVersion2. A complete doc

A Python class library of tools for learning agents, including reinforcement learning algorithms, function approximators, and vector quantizations algorithms. (Pronounced "plastic".)

Agents based reinforcement learning using Mathematica

Parallel Reinforcement Evolutionary Artificial Neural Networks (PREANN) is a framework of flexible multi-layer ANN's with reinforcement learning based on genetic algorithms and a parallel implementation (using XMM registers and NVIDIA's CUDA).

Physical Symbolic Optimization (Φ-SO) - A symbolic optimization package built for physics. Symbolic regression module uses deep reinforcement learning to infer analytical physical laws that fit data points, searching in the space of functional forms.

A Python translation of Piqle with Traits for simplified simulation with reinforcement learning agents.

RL Baselines Zoo is a comprehensive training framework and collection of pre-trained RL agents using Stable-Baselines3. It offers tools for training, tuning, and evaluating RL algorithms across many standard environments, including MuJoCo, Atari, and robotics simulations. Designed for reproducible RL research and benchmarking, it includes scripts, hyperparameter presets, and best practices for training robust agents.

RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold'em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.

RL++ is an easy to use modular open source library for Reinforcement Learning written in C++. It includes learning algorithms (TD, Sarsa, Q) as well as the implementation of value function representations (LookupTable, TileCoding, Neuronal Network).

RL-POMDP is a Reinforcement Learning (RL) based algorithm to find approximate and satisfactory solution to POMDP problems. RL-POMDP is orders of magnitude faster than exact POMDP solver.

A project to compare classic reinforcement learning algorithms on the Pong game.

Reinforcement learning and simulation-based search in computer Go

Learning NLG template parameter types with reinforcement learning.

Based on the rl-ggp project. Research & development project on General Game Playing and relational reinforcement learning.

Combining improvements in deep reinforcement learning. Results and pretrained models can be found in the releases. Data-efficient Rainbow can be run using several options (note that the "unbounded" memory is implemented here in practice by manually setting the memory capacity to be the same as the maximum number of timesteps).

This is my school project. It focuses on Reinforcement Learning for personalized news recommendation. The main distinction is that it tries to solve online off-policy learning with dynamically generated item embeddings. I want to create a library with SOTA algorithms for reinforcement learning recommendation, providing the level of abstraction you like.

Lecture notes, tutorial tasks including solutions as well as online videos for the reinforcement learning course hosted by Paderborn University. The source code for the entire course material is open and everyone is cordially invited to use it for self-learning (students) or to set up their own course (lecturers).

The ultimate Reinforcement Learning Simulator!!!

This is a third year computer science project. A software system for simulating and animating Reinforcement Learning (RL) algorithms mainly for modular robots.

Algorithms in Reinforcement Learning: An Introduction (Sutton and Barto)

A collection of tools for doing reinforcement learning research in Julia. Provide elaborately designed components and interfaces to help users implement new algorithms. Make it easy for new users to run benchmark experiments, compare different algorithms, and evaluate and diagnose agents. Facilitate reproducibility from traditional tabular methods to modern deep reinforcement learning algorithms. Make it easy for new users to run benchmark experiments, compare different algorithms, and evaluate and diagnose agents. Facilitate reproducibility from traditional tabular methods to modern deep reinforcement learning algorithms. Provide elaborately designed components and interfaces to help users implement new algorithms. A number of built-in environments and third-party environment wrappers are provided to evaluate algorithms in various scenarios.