A computational approach to visual ecology with deep reinforcement learning

• URL: http://arxiv.org/abs/2402.05266v1
• Date: Wed, 7 Feb 2024 21:23:47 GMT
• Title: A computational approach to visual ecology with deep reinforcement learning
• Authors: Sacha Sokoloski, Jure Majnik, Philipp Berens
• Abstract summary: This paper lays the foundation for a computational approach to visual ecology. It shows how representations and behaviour emerge from an agent's drive for survival.
• Score: 6.635611625764804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Animal vision is thought to optimize various objectives from metabolic efficiency to discrimination performance, yet its ultimate objective is to facilitate the survival of the animal within its ecological niche. However, modeling animal behavior in complex environments has been challenging. To study how environments shape and constrain visual processing, we developed a deep reinforcement learning framework in which an agent moves through a 3-d environment that it perceives through a vision model, where its only goal is to survive. Within this framework we developed a foraging task where the agent must gather food that sustains it, and avoid food that harms it. We first established that the complexity of the vision model required for survival on this task scaled with the variety and visual complexity of the food in the environment. Moreover, we showed that a recurrent network architecture was necessary to fully exploit complex vision models on the most visually demanding tasks. Finally, we showed how different network architectures learned distinct representations of the environment and task, and lead the agent to exhibit distinct behavioural strategies. In summary, this paper lays the foundation for a computational approach to visual ecology, provides extensive benchmarks for future work, and demonstrates how representations and behaviour emerge from an agent's drive for survival.

Related papers

• A neuromorphic model of the insect visual system for natural image processing [0.8602553195689513]
  Insect vision supports complex behaviors including associative learning, navigation, and object detection.<n>Here, we introduce a bio-inspired vision model that transforms dense visual input into sparse, discriminative codes.<n>We evaluate the resulting representations on flower recognition tasks and natural image benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T05:54:28Z)
• Do-Undo: Generating and Reversing Physical Actions in Vision-Language Models [57.71440995598757]
  We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models.<n>Do-Undo requires models to simulate the outcome of a physical action and then accurately reverse it, reflecting true cause-and-effect in the visual world.
  arXiv  Detail & Related papers  (2025-12-15T18:03:42Z)
• Vision encoders should be image size agnostic and task driven [60.09702846704075]
  We focus on a couple of ways in which vision in nature is efficient, but modern vision encoders not.<n>It is our belief that vision encoders should be dynamic and the computational complexity should depend on the task at hand rather than the size of the image.
  arXiv  Detail & Related papers  (2025-08-22T11:57:49Z)
• Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation [14.157948867532832]
  We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Motivated by this, we propose a framework for perspective-aware reasoning, named Abstract Perspective Change (APC) Our experiments on synthetic and real-image benchmarks, compared with various VLMs, demonstrate significant improvements in perspective-aware reasoning with our framework.
  arXiv  Detail & Related papers  (2025-04-24T02:41:34Z)
• A Simulation Environment for the Neuroevolution of Ant Colony Dynamics [0.0]
  We introduce a simulation environment to facilitate research into emergent collective behaviour. By leveraging real-world data, the environment simulates a target ant trail that a controllable agent must learn to replicate.
  arXiv  Detail & Related papers  (2024-06-19T01:51:15Z)
• Enhancing Graph Representation of the Environment through Local and Cloud Computation [2.9465623430708905]
  We propose a graph-based representation that provides a semantic representation of robot environments from multiple sources. To acquire information from the environment, the framework combines classical computer vision tools with modern computer vision cloud services. The proposed approach allows us to handle also small objects and integrate them into the semantic representation of the environment.
  arXiv  Detail & Related papers  (2023-09-22T08:05:32Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• Bridging the Gap to Real-World Object-Centric Learning [66.55867830853803]
  We show that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing object-centric learning models on simulated data.
  arXiv  Detail & Related papers  (2022-09-29T15:24:47Z)
• The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents [51.94554095091305]
  We argue for an introspective agent, which considers its own abilities in the context of its environment. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment.
  arXiv  Detail & Related papers  (2022-01-02T20:14:01Z)
• Information is Power: Intrinsic Control via Information Capture [110.3143711650806]
  We argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states.
  arXiv  Detail & Related papers  (2021-12-07T18:50:42Z)
• Unadversarial Examples: Designing Objects for Robust Vision [100.4627585672469]
  We develop a framework that exploits the sensitivity of modern machine learning algorithms to input perturbations in order to design "robust objects" We demonstrate the efficacy of the framework on a wide variety of vision-based tasks ranging from standard benchmarks to (in-simulation) robotics.
  arXiv  Detail & Related papers  (2020-12-22T18:26:07Z)
• Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects [63.89096733478149]
  We introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects. We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills jointly. We demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.
  arXiv  Detail & Related papers  (2020-12-22T17:52:29Z)
• Embodied Visual Active Learning for Semantic Segmentation [33.02424587900808]
  We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding. We develop a battery of agents - both learnt and pre-specified - and with different levels of knowledge of the environment. We extensively evaluate the proposed models using the Matterport3D simulator and show that a fully learnt method outperforms comparable pre-specified counterparts.
  arXiv  Detail & Related papers  (2020-12-17T11:02:34Z)
• Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps [0.0]
  Humans learn by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.
  arXiv  Detail & Related papers  (2020-07-03T12:29:11Z)
• Ecological Reinforcement Learning [76.9893572776141]
  We study the kinds of environment properties that can make learning under such conditions easier. understanding how properties of the environment impact the performance of reinforcement learning agents can help us to structure our tasks in ways that make learning tractable.
  arXiv  Detail & Related papers  (2020-06-22T17:55:03Z)

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.