Skip to content
Back to skills

Multiobjective Modelbased Policy Search For Dataefficient Learning With Sparse Rewards

ASecurity

**arXiv ID:** 1806.09351 **Authors:** Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret **Published:** 2018-06-25T09:46:47Z **Abstract:** The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effective exploration str...

  • 3 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 11, 2026
toolsgo

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill multiobjective-modelbased-policy-search-for-dataefficient-learning-with-sparse-rewards --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Multiobjective Modelbased Policy Search For Dataefficient Learning With Sparse Rewards?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Multiobjective Modelbased Policy Search For Dataefficient Learning With Sparse Rewards
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-multiobjective-modelbased-policy-search-for-dataef/badge)](https://www.skillsdirectory.com/skills/hiyenwong-multiobjective-modelbased-policy-search-for-dataef)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards

**arXiv ID:** 1806.09351
**Authors:** Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret
**Published:** 2018-06-25T09:46:47Z
**Abstract:**
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effective exploration strategy to deal with sparse or misleading reward scenarios: if they do not experience any state with a positive reward during the initial random exploration, it is very unlikely to solve the problem. Here, we propose a novel model-based policy search algorithm, Multi-DEX, that leverages a learned dynamical model to efficiently explore the task space and solve tasks with sparse rewards in a few episodes. To achieve this, we frame the policy search problem as a multi-objective, model-based policy optimization problem with three objectives: (1) generate maximally novel state trajectories, (2) maximize the expected return and (3) keep the system in state-space regions for which the model is as accurate as possible. We then optimize these objectives using a Pareto-based multi-objective optimization algorithm. The experiments show that Multi-DEX is able to solve sparse reward scenarios (with a simulated robotic arm) in much lower interaction time than VIME, TRPO, GEP-PG, CMA-ES and Black-DROPS.

## Skill Description

This skill is generated from the arXiv paper: Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards (1806.09351).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1806.09351](http://arxiv.org/abs/1806.09351v3)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.