* External authors




Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Bo Liu*

Yihao Feng*

Qiang Liu*

Peter Stone

* External authors

AAAI 2023



Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the agent is only rewarded when it reaches its goal. While several methods have been proposed to improve the sample efficiency of GCRL, one relatively under-studied approach is the design of neural architectures to support sample efficiency. In this work, we introduce a novel neural architecture for GCRL that achieves significantly better sample efficiency than the commonly-used monolithic network architecture. The key insight is that the optimal action-value function Q^*(s, a, g) must satisfy the triangle inequality in a specific sense. Furthermore, we introduce the metric residual network (MRN) that deliberately decomposes the action-value function Q(s,a,g) into the negated summation of a metric plus a residual asymmetric component. MRN provably approximates any optimal action-value function Q^*(s,a,g), thus making it a fitting neural architecture for GCRL. We conduct comprehensive experiments across 12 standard benchmark environments in GCRL. The empirical results demonstrate that MRN uniformly outperforms other state-of-the-art GCRL neural architectures in terms of sample efficiency.

Related Publications

VaryNote: A Method to Automatically Vary the Number of Notes in Symbolic Music

CMMR, 2023
Juan M. Huerta*, Bo Liu*, Peter Stone

Automatically varying the number of notes in symbolic music has various applications in assisting music creators to embellish simple tunes or to reduce complex music to its core idea. In this paper, we formulate the problem of varying the number of notes while preserving the…

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

NeurIPS, 2023
Bo Liu*, Yifeng Zhu*, Chongkai Gao*, Yihao Feng*, Qiang Liu*, Yuke Zhu*, Peter Stone

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and conce…

FAMO: Fast Adaptive Multitask Optimization

NeurIPS, 2023
Bo Liu*, Yihao Feng*, Peter Stone, Qiang Liu*

One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL). However, gradient descent (GD) on the average loss across all tasks may yield poor multitask performance due to severe…

  • HOME
  • Publications
  • Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.