general-reinforcement-learning-3

Model-based Reinforcement Learning

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in general-reinforcement-learning-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find general-reinforcement-learning-3 models and implementations

opendilab/DI-engine

3 papers 2,778

Datasets

POPGym

Subtasks

No subtasks available.

Most implemented papers

When to Trust Your Model: Model-Based Policy Optimization

S. Levine, Justin Fu, Michael Janner, Marvin Zhang•Tue Jun 18 2019

This paper first formulate and analyze a model-based reinforcement learning algorithm with a guarantee of monotonic improvement at each step, and demonstrates that a simple procedure of using short model-generated rollouts branched from real data has the benefits of more complicated model- based algorithms without the usual pitfalls.

1114

Content

facebookresearch/mbrl-lib

3 papers 932

natolambert/dynamicslearn

3 papers 54

google-research/dads

2 papers 185

0

Paper Graph

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

S. Levine, Kurtland Chua, R. Calandra, R. McAllister•Tue May 29 2018

This paper proposes a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation, which matches the asymptotic performance of model-free algorithms on several challenging benchmark tasks, while requiring significantly fewer samples.

1383 0

Paper Graph

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

S. Levine, Anusha Nagabandi, G. Kahn, R. Fearing•Mon Aug 07 2017

It is demonstrated that neural network dynamics models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning algorithm, producing stable and plausible gaits that accomplish various complex locomotion tasks.

1033 0

Paper Graph

Machine Learning and System Identification for Estimation in Physical Systems

Fredrik Bagge Carlson•Wed Dec 19 2018

This thesis develops methods that are practically motivated and ensure that they are implementable also outside the research setting, by performing experiments in realistic settings and providing open-source implementations of all proposed methods and algorithms.

7 0

Paper Graph

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

Jan Peters, Paavo Parmas, C. Rasmussen, K. Doya•Sun Feb 03 2019

A model-based policy search framework, Probabilistic Inference for Particle-Based Policy Search (PIPPS), which is easily extensible, and allows for almost arbitrary models and policies, while simultaneously matching the performance of previous data-efficient learning algorithms.

93 0

Paper Graph

Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning

D. Meger, J. A. G. Higuera, G. Dudek•Mon Mar 05 2018

An algorithm for rapidly learning neural network policies for robotics systems that follows the model-based reinforcement learning paradigm and improves upon existing algorithms: PILeO and a sample-based version of PILeo with neural network dynamics (Deep-PILeO).

40 0

Paper Graph

Dynamics-Aware Unsupervised Discovery of Skills

S. Levine, Vikash Kumar, S. Gu, Karol Hausman, Archit Sharma•Mon Jul 01 2019

This work proposes an unsupervised learning algorithm, Dynamics-Aware Discovery of Skills (DADS), which simultaneously discovers predictable behaviors and learns their dynamics, and demonstrates that zero-shot planning in the learned latent space significantly outperforms standard MBRL and model-free goal-conditioned RL, and substantially improves over prior hierarchical RL methods for unsuper supervised skill discovery.

460 0

Paper Graph

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

Jian Guan, Hongning Wang, Xueying Bai•Sat Nov 09 2019

This work proposes a model-based reinforcement learning solution which models user-agent interaction for offline policy learning via a generative adversarial network and uses a discriminator to evaluate the quality of generated data and scale the generated rewards.

81 0

Paper Graph

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

Amy Zhang, R. Calandra, Nathan Lambert, Brandon Amos, Luis Pineda•Mon Apr 19 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.

53 0

Paper Graph

Temporal Predictive Coding For Model-Based Planning In Latent Space

Stefano Ermon, Tung D. Nguyen, Rui Shu, Tu Pham, H. Bui•Sun Jun 13 2021

This work presents an information-theoretic approach that employs temporal predictive coding to encode elements in the environment that can be predicted across time that is superior to existing methods in the challenging complex-background setting while remaining competitive with current state-of-the-art models in the standard setting.

62 0

Paper Graph

Adding a benchmark result helps the community track progress.