Co-Imitation: Learning Design and Behaviour by Imitation
- URL: http://arxiv.org/abs/2209.01207v1
- Date: Fri, 2 Sep 2022 17:57:32 GMT
- Title: Co-Imitation: Learning Design and Behaviour by Imitation
- Authors: Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck,
Ville Kyrki
- Abstract summary: Co-adaptation of robots aims to adapt both body and behaviour of a system for a given task.
This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation.
We propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator.
- Score: 10.40773958250192
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The co-adaptation of robots has been a long-standing research endeavour with
the goal of adapting both body and behaviour of a system for a given task,
inspired by the natural evolution of animals. Co-adaptation has the potential
to eliminate costly manual hardware engineering as well as improve the
performance of systems. The standard approach to co-adaptation is to use a
reward function for optimizing behaviour and morphology. However, defining and
constructing such reward functions is notoriously difficult and often a
significant engineering effort. This paper introduces a new viewpoint on the
co-adaptation problem, which we call co-imitation: finding a morphology and a
policy that allow an imitator to closely match the behaviour of a demonstrator.
To this end we propose a co-imitation methodology for adapting behaviour and
morphology by matching state distributions of the demonstrator. Specifically,
we focus on the challenging scenario with mismatched state- and action-spaces
between both agents. We find that co-imitation increases behaviour similarity
across a variety of tasks and settings, and demonstrate co-imitation by
transferring human walking, jogging and kicking skills onto a simulated
humanoid.
Related papers
- Life, uh, Finds a Way: Systematic Neural Search [2.163881720692685]
We tackle the challenge of rapidly adapting an agent's behavior to solve continuous problems in settings.
Instead of focusing on deep reinforcement learning, we propose viewing behavior as the physical manifestation of a search procedure.
We describe an algorithm that implicitly enumerates behaviors by regulating the tight feedback loop between execution of behaviors and mutation of the graph.
arXiv Detail & Related papers (2024-10-02T09:06:54Z) - Cognitive Evolutionary Learning to Select Feature Interactions for Recommender Systems [59.117526206317116]
We show that CELL can adaptively evolve into different models for different tasks and data.
Experiments on four real-world datasets demonstrate that CELL significantly outperforms state-of-the-art baselines.
arXiv Detail & Related papers (2024-05-29T02:35:23Z) - Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment [92.48012013825988]
We study the problem of adapting on-the-fly to novel scenarios during deployment.
Our approach, RObust Autonomous Modulation (ROAM), introduces a mechanism based on the perceived value of pre-trained behaviors.
We demonstrate that ROAM enables a robot to adapt rapidly to changes in dynamics both in simulation and on a real Go1 quadruped.
arXiv Detail & Related papers (2023-11-02T08:22:28Z) - Leveraging Human Feedback to Evolve and Discover Novel Emergent
Behaviors in Robot Swarms [14.404339094377319]
We seek to leverage human input to automatically discover a taxonomy of collective behaviors that can emerge from a particular multi-agent system.
Our proposed approach adapts to user preferences by learning a similarity space over swarm collective behaviors.
We test our approach in simulation on two robot capability models and show that our methods consistently discover a richer set of emergent behaviors than prior work.
arXiv Detail & Related papers (2023-04-25T15:18:06Z) - Inferring Versatile Behavior from Demonstrations by Matching Geometric
Descriptors [72.62423312645953]
Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps.
Current Imitation Learning algorithms often only consider unimodal expert demonstrations and act in a state-action-based setting.
Instead, we combine a mixture of movement primitives with a distribution matching objective to learn versatile behaviors that match the expert's behavior and versatility.
arXiv Detail & Related papers (2022-10-17T16:42:59Z) - Modelling Behaviour Change using Cognitive Agent Simulations [0.0]
This paper presents work-in-progress research to apply selected behaviour change theories to simulated agents.
The research is focusing on complex agent architectures required for self-determined goal achievement in adverse circumstances.
arXiv Detail & Related papers (2021-10-16T19:19:08Z) - 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) - 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) - Learning Compliance Adaptation in Contact-Rich Manipulation [81.40695846555955]
We propose a novel approach for learning predictive models of force profiles required for contact-rich tasks.
The approach combines an anomaly detection based on Bidirectional Gated Recurrent Units (Bi-GRU) and an adaptive force/impedance controller.
arXiv Detail & Related papers (2020-05-01T05:23:34Z) - Environmental Adaptation of Robot Morphology and Control through
Real-world Evolution [5.08706161686979]
We apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot.
We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology.
arXiv Detail & Related papers (2020-03-30T07:57:19Z)
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.