LGMLMay 28, 2019

Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy

arXiv:1905.11583v1
Originality Incremental advance
AI Analysis

This addresses the challenge of inefficient exploration in RL for robotics and simulation domains, but it is incremental as it builds on existing meta-learning and exploration methods.

The paper tackles the problem of learning task-agnostic exploration policies in reinforcement learning by proposing a counterfactual metric and meta-learning approach, achieving good results in high-dimensional MuJoCo control tasks.

A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for exploration involve task-agnostic design, that is performing well in one environment, but be ill-suited to another. To the purpose of learning an effective and efficient exploration policy in an automated manner. We formalized a feasible metric for measuring the utility of exploration based on counterfactual ideology. Based on that, We proposed an end-to-end algorithm to learn exploration policy by meta-learning. We demonstrate that our method achieves good results compared to previous works in the high-dimensional control tasks in MuJoCo simulator.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes