Meta-learning curiosity algorithms

• URL: http://arxiv.org/abs/2003.05325v1
• Date: Wed, 11 Mar 2020 14:25:43 GMT
• Title: Meta-learning curiosity algorithms
• Authors: Ferran Alet, Martin F. Schneider, Tomas Lozano-Perez, Leslie Pack Kaelbling
• Abstract summary: We formulate the problem of generating curious behavior as one of meta-learning. Our rich language of programs combines neural networks with other building blocks such as buffers, nearest-neighbor modules and custom loss functions. We find two novel curiosity algorithms that perform on par or better than human-designed published curiosity algorithms in domains as disparate as grid navigation with image inputs, acrobot, lunar lander, ant and hopper.
• Score: 26.186627089223624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We formulate the problem of generating curious behavior as one of meta-learning: an outer loop will search over a space of curiosity mechanisms that dynamically adapt the agent's reward signal, and an inner loop will perform standard reinforcement learning using the adapted reward signal. However, current meta-RL methods based on transferring neural network weights have only generalized between very similar tasks. To broaden the generalization, we instead propose to meta-learn algorithms: pieces of code similar to those designed by humans in ML papers. Our rich language of programs combines neural networks with other building blocks such as buffers, nearest-neighbor modules and custom loss functions. We demonstrate the effectiveness of the approach empirically, finding two novel curiosity algorithms that perform on par or better than human-designed published curiosity algorithms in domains as disparate as grid navigation with image inputs, acrobot, lunar lander, ant and hopper.

Related papers

• Curiosity-Driven Reinforcement Learning based Low-Level Flight Control [95.42181254494287]
  This work proposes an algorithm based on the drive of curiosity for autonomous learning to control by generating proper motor speeds from odometry data. We ran tests using on-policy, off-policy, on-policy plus curiosity, and the proposed algorithm and visualized the effect of curiosity in evolving exploration patterns.
  arXiv  Detail & Related papers  (2023-07-28T11:46:28Z)
• Navigating to Objects in the Real World [76.1517654037993]
  We present a large-scale empirical study of semantic visual navigation methods comparing methods from classical, modular, and end-to-end learning approaches. We find that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% simulation to 23% real-world success rate due to a large image domain gap between simulation and reality.
  arXiv  Detail & Related papers  (2022-12-02T01:10:47Z)
• Neural Routing in Meta Learning [9.070747377130472]
  We aim to improve the model performance of the current meta learning algorithms by selectively using only parts of the model conditioned on the input tasks. In this work, we describe an approach that investigates task-dependent dynamic neuron selection in deep convolutional neural networks (CNNs) by leveraging the scaling factor in the batch normalization layer. We find that the proposed approach, neural routing in meta learning (NRML), outperforms one of the well-known existing meta learning baselines on few-shot classification tasks.
  arXiv  Detail & Related papers  (2022-10-14T16:31:24Z)
• Improving exploration in policy gradient search: Application to symbolic optimization [6.344988093245026]
  Many machine learning strategies leverage neural networks to search large spaces of mathematical symbols. In contrast to traditional evolutionary approaches, using a neural network at the core of the search allows learning higher-level symbolic patterns. We show that these techniques can improve the performance, increase sample efficiency, and lower the complexity of solutions for the task of symbolic regression.
  arXiv  Detail & Related papers  (2021-07-19T21:11:07Z)
• MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning [65.52675802289775]
  We show that an uncertainty aware classifier can solve challenging reinforcement learning problems. We propose a novel method for computing the normalized maximum likelihood (NML) distribution. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions.
  arXiv  Detail & Related papers  (2021-07-15T08:19:57Z)
• Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
  We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
  arXiv  Detail & Related papers  (2021-07-10T19:02:27Z)
• A Study of the Mathematics of Deep Learning [1.14219428942199]
  "Deep Learning"/"Deep Neural Nets" is a technological marvel that is now increasingly deployed at the cutting-edge of artificial intelligence tasks. This thesis takes several steps towards building strong theoretical foundations for these new paradigms of deep-learning.
  arXiv  Detail & Related papers  (2021-04-28T22:05:54Z)
• Meta-Gradient Reinforcement Learning with an Objective Discovered Online [54.15180335046361]
  We propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network. Because the objective is discovered online, it can adapt to changes over time. On the Atari Learning Environment, the meta-gradient algorithm adapts over time to learn with greater efficiency.
  arXiv  Detail & Related papers  (2020-07-16T16:17:09Z)
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch [76.83052807776276]
  We show that it is possible to automatically discover complete machine learning algorithms just using basic mathematical operations as building blocks. We demonstrate this by introducing a novel framework that significantly reduces human bias through a generic search space. We believe these preliminary successes in discovering machine learning algorithms from scratch indicate a promising new direction in the field.
  arXiv  Detail & Related papers  (2020-03-06T19:00:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.