A clean PyTorch implementation of PPO, SAC, and TD3 made from scratch. It is built for testing and comparing continuous control RL algorithms on complex environments such as BipedalWalker-v3.

Area práctica de Técnicas Digitales 3 UTN FRM

PyTorch implementation of off-policy RL algorithms (TD3 and SAC). Tested in OpenAI Gymnasium.

Distributed Deep Learning framework based on Tensorflow2

TD3 Reinforcement Learning Implementation Project

Fun with Reinforcement Learning in my spare time

Implementation of some deep RL algorithms

Implementation of (Deep) Reinforcement Learning algorithms using PyTorch & TensorFlow2

Reinforcement Learning Agents for Analog Circuit Sizing in Haskell.

Twin Delayed DDPG

Implementation of DDPG in Pytorch with live logging via visdom

reinforcement learning framework with pytorch

Official Repository for The Paper, Beyond Multi‑Agent Reinforcement Learning: Scalable Centralized Control for Large-Scale Dynamic Trip-Vehicle Assignment

Teaching an bipedal bot how to walk using a TD3 algorithm (variant of Reinforcement Learning - Actor & Critic method)

RL-Odyssey is a research framework for continuous control that implements state-of-the-art RL algorithms (SAC, TD3, PPO, etc.) with clean experiment scripts and interactive notebooks.

Empirical study of over-estimation bias in DDPG vs TD3 on LunarLanderContinuous-v3.

Deep Deterministic Policy Gradient implementation for Reinforcement Learning course taught at Aalto University.

R²PA — Regime-aware reinforcement learning for portfolio allocation (RL, regime signals, LLM oracle)

Example TD3 implementation with ReLAx