| title | abstract | keywords | layout | series | id | month | tex_title | firstpage | lastpage | page | order | cycles | bibtex_author | author | date | address | publisher | container-title | volume | genre | issued | extras | |||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards |
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 cumulative reward 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. |
Model-based Policy Search, Exploration, Sparse Reward |
inproceedings |
Proceedings of Machine Learning Research |
kaushik18a |
0 |
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards |
839 |
855 |
839-855 |
839 |
false |
Kaushik, Rituraj and Chatzilygeroudis, Konstantinos and Mouret, Jean-Baptiste |
|
2018-10-23 |
PMLR |
Proceedings of The 2nd Conference on Robot Learning |
87 |
inproceedings |
|
|