RAD: Reinforcement Learning with Augmented Data
-
Updated
Mar 29, 2021 - Jupyter Notebook
RAD: Reinforcement Learning with Augmented Data
DrQ: Data regularized Q
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Curvature Corrected Moving Average: An accurate and model-free path smoothing algorithm.
ExORL: Exploratory Data for Offline Reinforcement Learning
The Reinforcement-Learning-Related Papers of ICLR 2019
Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http:https://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"
Implementation of Soft Actor Critic and some of its improvements in Pytorch
Implementation of the CartPole from OpenAI's Gym using only visual input for Reinforcement Learning control with DQN
A Pytorch implementation of The Visual Centrifuge: Model-Free Layered Video Representations.
Code for IEEE MLSP 2021 paper titled "Model-Free Learning of Optimal Deterministic Resource Allocations in Wireless Systems via Action-Space Exploration"
DDPG and D4PG Continuous Control
Deep Reinforcement Learning implementation in Keras of an AI controlling the popular Flappy Bird videogame, using Asynchronous Advantage Actor Critic (A3C)
Sample Policy Gradient
Network inference via Event Space Linearization (ESL)
A Python package for Robot Learning
This repository hosts the code accompanying the paper "Model-Free Active Exploration in Reinforcement Learning". Our study approaches the exploration problem in Reinforcement Learning (RL) from an information-theoretical viewpoint and presents a novel, efficient, and entirely model-free solution.
This presentation contains very precise yet detailed explanation of concepts of a very interesting topic -- Reinforcement Learning.
Project for the course "Foundations of Reinforcement Learning" 2021 at ETH Zurich
Implementation of k-Step Latent (KSL)
Add a description, image, and links to the model-free topic page so that developers can more easily learn about it.
To associate your repository with the model-free topic, visit your repo's landing page and select "manage topics."