Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
This addresses a key bottleneck in robotics for enabling efficient learning in real-world tasks with limited feedback, though it is an incremental improvement over prior model-based methods.
The paper tackles the problem of data-efficient reinforcement learning in robotics with sparse rewards by proposing Multi-DEX, a model-based policy search algorithm that frames policy optimization as a multi-objective problem to enhance exploration; experiments show it solves sparse reward scenarios in simulated robotic arms with significantly lower interaction time than existing methods like VIME and TRPO.
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.