Reinforcement Learning
Showing 23 of 167 projects
Modular framework for Reinforcement Learning in python
A JAX-powered reimplementation of MiniGrid offering over 1000x speedup for reinforcement learning experiments.
A trading environment for reinforcement learning agents, supporting backtesting, live trading, and multiple RL algorithms.
A neuroevolution-based trading bot that evolves populations of neural networks to trade cryptocurrency using technical analysis.
Safe Bayesian Optimization
A simple C++ library for multi-armed bandit simulations with multiple policy implementations.
A collection of neuroevolution experiments for reinforcement learning control problems using unsupervised learning feature extractors.
A Python webserver for setting up and running contextual multi-armed bandit experiments with customizable policies.
A Go implementation of the NEAT (NeuroEvolution of Augmenting Topologies) algorithm for evolving neural network structures.
A simple implementation of the DAGGER imitation learning algorithm for autonomous steering control in the Torcs racing simulator.
A Gymnasium-based benchmarking suite with realistic environments for evaluating reinforcement learning algorithms in practical scenarios.
A PyTorch framework for reinforcement learning research, focused on reproducibility and fast experimentation.
A Lua-driven AI that plays Game Boy Color games through experimentation and learning.
A reinforcement learning toolbox implementing TRPO and A3C algorithms for continuous action spaces.
A collection of academic papers and code implementations for quantitative trading strategies.
A comprehensive Ruby gem providing atomic, flexible tools and frameworks for practical machine learning applications.
A comprehensive Ruby gem providing a collection of atomic machine learning tools and frameworks for practical applications.
Scripts to generate a dataset with static frames from the Arcade Learning Environment for Atari games.
A framework for writing AI agents to battle in Pokémon Showdown, supporting both online and offline simulations.
A VS Code extension to view and compare Weights & Biases training runs directly in the editor with interactive charts and AI context export.
A 2048 game implementation in V with multiple AI algorithms including DFS, heuristic, minimax, expectimax, Monte Carlo, and reinforcement learning.
A dynamic inference wrapper for Transformer language models that enables per-token layer skipping to reduce computational FLOPs.
A Python library for simulating spiking neural networks (SNNs) using PyTorch, geared towards biologically inspired machine learning.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.