Model-based Reinforcement Learning

169 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Model-based Reinforcement Learning models and implementations


Most implemented papers

When to Trust Your Model: Model-Based Policy Optimization

JannerM/mbpo NeurIPS 2019

Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data.

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

kchua/handful-of-trials NeurIPS 2018

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance.

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

anagabandi/nn_dynamics 8 Aug 2017

Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, but typically require a very large number of samples to achieve good performance.

Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning

juancamilog/kusanagi 6 Mar 2018

Finally, we assess the performance of the algorithm for learning motor controllers for a six legged autonomous underwater vehicle.

PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos

proppo/pipps_demo ICML 2018

Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization.

Machine Learning and System Identification for Estimation in Physical Systems

baggepinnen/Robotlib.jl 5 Jun 2019

The main approach to estimation and learning adopted is optimization based.

Dynamics-Aware Unsupervised Discovery of Skills

google-research/dads 2 Jul 2019

Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment.

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

JianGuanTHU/IRecGAN NeurIPS 2019

Reinforcement learning is well suited for optimizing policies of recommender systems.

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

facebookresearch/mbrl-lib 20 Apr 2021

MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms.

Temporal Predictive Coding For Model-Based Planning In Latent Space

VinAIResearch/TPC-tensorflow 14 Jun 2021

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments.