trust-region-policy-optimization

This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)

PyTorch implementation of Trust Region Policy Optimization

A trading bitcoin agent was created with deep reinforcement learning implementations.

Python implementation of some numerical (optimization) methods

A collection of Reinforcement Learning implementations with PyTorch

Trust Region Policy Optimization (TRPO) in pure TensorFlow

Official implementation of the AAAI 2021 paper Deep Bayesian Quadrature Policy Optimization.

Benchmarking the Natural Gradient in Policy Gradient Methods and Evolution Strategies

works about solving nonlinear dynamic systems

Undergraduate Dissertation (University of Malta) 2020-2023 - 'Autonomous Drone Control using Reinforcement Learning''

My solutions to the labs from this bootcamp:

Course projects of CS395T Numerical Optimization, UT Austin

Implementation of all RL algorithms in a simpler way

A short and self-contained tutorial on Trust Region Policy Optimisation motivated from Vanilla Policy Gradient

Code for the ICML 2024 paper 'GFlowNet Training by Policy Gradients'

Deep Reinforcement Learning from mathematical foundations to PyTorch implementations: rigorous proofs, step-by-step derivations of objectives and gradient estimators, and reproducible experiments on Gymnasium and MuJoCo benchmarks spanning policy gradients, actor-critic methods, value-based learning, and continuous control.

The pytorch implemetation of trpo

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.

Scheduling TRPO's KL Divergence Constraint