Evolving Reservoirs for Meta Reinforcement Learning

• URL: http://arxiv.org/abs/2312.06695v2
• Date: Mon, 29 Jan 2024 16:08:12 GMT
• Title: Evolving Reservoirs for Meta Reinforcement Learning
• Authors: Corentin L\'eger and Gautier Hamon and Eleni Nisioti and Xavier Hinaut and Cl\'ement Moulin-Frier
• Abstract summary: We propose a computational model for studying a mechanism that can enable such a process. At the evolutionary scale, we evolve reservoirs, a family of recurrent neural networks. We employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL) Our results show that the evolution of reservoirs can improve the learning of diverse challenging tasks.
• Score: 1.6874375111244329
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Animals often demonstrate a remarkable ability to adapt to their environments during their lifetime. They do so partly due to the evolution of morphological and neural structures. These structures capture features of environments shared between generations to bias and speed up lifetime learning. In this work, we propose a computational model for studying a mechanism that can enable such a process. We adopt a computational framework based on meta reinforcement learning as a model of the interplay between evolution and development. At the evolutionary scale, we evolve reservoirs, a family of recurrent neural networks that differ from conventional networks in that one optimizes not the synaptic weights, but hyperparameters controlling macro-level properties of the resulting network architecture. At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL). Within an RL agent, a reservoir encodes the environment state before providing it to an action policy. We evaluate our approach on several 2D and 3D simulated environments. Our results show that the evolution of reservoirs can improve the learning of diverse challenging tasks. We study in particular three hypotheses: the use of an architecture combining reservoirs and reinforcement learning could enable (1) solving tasks with partial observability, (2) generating oscillatory dynamics that facilitate the learning of locomotion tasks, and (3) facilitating the generalization of learned behaviors to new tasks unknown during the evolution phase.

Related papers

• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• Generative Adversarial Neuroevolution for Control Behaviour Imitation [3.04585143845864]
  We propose to explore whether deep neuroevolution can be used for behaviour imitation on popular simulation environments. We introduce a simple co-evolutionary adversarial generation framework, and evaluate its capabilities by evolving standard deep recurrent networks. Across all tasks, we find the final elite actor agents capable of achieving scores as high as those obtained by the pre-trained agents.
  arXiv  Detail & Related papers  (2023-04-03T16:33:22Z)
• Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks [6.760855795263126]
  Spiking Neural Network (SNN) based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired intelligence. This paper presents a novel LSM learning model that integrates adaptive structural evolution and multi-scale biological learning rules.
  arXiv  Detail & Related papers  (2023-03-31T07:36:39Z)
• Developing hierarchical anticipations via neural network-based event segmentation [14.059479351946386]
  We model the development of hierarchical predictions via autonomously learned latent event codes. We present a hierarchical recurrent neural network architecture, whose inductive learning biases foster the development of sparsely changing latent state. A higher level network learns to predict the situations in which the latent states tend to change.
  arXiv  Detail & Related papers  (2022-06-04T18:54:31Z)
• 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)
• Epigenetic evolution of deep convolutional models [81.21462458089142]
  We build upon a previously proposed neuroevolution framework to evolve deep convolutional models. We propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator.
  arXiv  Detail & Related papers  (2021-04-12T12:45:16Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• Continual Developmental Neurosimulation Using Embodied Computational Agents [0.0]
  Continual developmental neurosimulation allows us to consider the role of developmental trajectories in bridging the related phenomena of nervous system morphogenesis, developmental learning, and plasticity. Our approach is tightly integrated with developmental embodiment, and can be implemented using a type of agent called developmental Braitenberg Vehicles (dBVs) dBVs begin their lives as a set of undefined structures that transform into agent-based systems including a body, sensors, effectors, and nervous system.
  arXiv  Detail & Related papers  (2021-03-07T07:22:49Z)
• Task-Agnostic Morphology Evolution [94.97384298872286]
  Current approaches that co-adapt morphology and behavior use a specific task's reward as a signal for morphology optimization. This often requires expensive policy optimization and results in task-dependent morphologies that are not built to generalize. We propose a new approach, Task-Agnostic Morphology Evolution (TAME), to alleviate both of these issues.
  arXiv  Detail & Related papers  (2021-02-25T18:59:21Z)
• Embodied Intelligence via Learning and Evolution [92.26791530545479]
  We show that environmental complexity fosters the evolution of morphological intelligence. We also show that evolution rapidly selects morphologies that learn faster. Our experiments suggest a mechanistic basis for both the Baldwin effect and the emergence of morphological intelligence.
  arXiv  Detail & Related papers  (2021-02-03T18:58:31Z)

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.