Publication

Learning with AMIGo: Adversarially Motivated Intrinsic Goals

International Conference on Learning Representations (ICLR)


Abstract

A key challenge for reinforcement learning (RL) consists of learning in environments with sparse extrinsic rewards. In contrast to current RL methods, humans are able to learn new skills with little or no reward by using various forms of intrinsic motivation. We propose AMIGO, a novel agent incorporating—as form of meta-learning—a goal-generating teacher that proposes Adversarially Motivated Intrinsic GOals to train a goal-conditioned “student” policy in the absence of (or alongside) environment reward. Specifically, through a simple but effective “constructively adversarial” objective, the teacher learns to propose increasingly challenging—yet achievable—goals that allow the student to learn general skills for acting in a new environment, independent of the task to be solved. We show that our method generates a natural curriculum of self-proposed goals which ultimately allows the agent to solve challenging procedurally-generated tasks where other forms of intrinsic motivation and state-of-the-art RL methods fail.

Related Publications

All Publications

IROS - September 27, 2021

Joint Sampling and Trajectory Optimization over Graphs for Online Motion Planning

Kalyan Vasudev Alwala, Mustafa Mukadam

RecSys - September 27, 2021

Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation

Gabriel De Souza Pereira Moreira, Sara Rabhi, Jeong Min Lee, Ronay Ak, Even Oldridge

EMNLP - October 31, 2021

Evaluation Paradigms in Question Answering

Pedro Rodriguez, Jordan Boyd-Graber

ASRU - December 13, 2021

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems

Yangyang Xia, Buye Xu, Anurag Kumar

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy