The effects of morphology and fitness on catastrophic interference

Powers, Joshua; Kriegman, Sam; Bongard, Josh

doi:10.1162/isal_a_00111

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to [22], we optimize both controllers for all experimented fixed morphologies (see Figure 5) jointly. Inspired by [45], we use the minimum performance among all morphologies as the fitness values for the controllers. 10 trials for each type of controller, initialized with different random seeds, are evolved for 5000 generations.…”

Section: Optimization On Multiple Fixed Morphologiesmentioning

confidence: 99%

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Mertan

Cheney

2023

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

Figure 1: Main hypothesis: In the brain-body co-optimization of soft robots, the locomotion performance of modular controllers is significantly more robust than global controllers to perturbations of their robot's morphology. This allows better transfer of that controller to a robot's offspring with morphological mutations. This increases the rate of successful morphological mutations during the co-optimization process and leads to a more efficient and effective search over robot designs.

show abstract

Section: Optimization On Multiple Fixed Morphologiesmentioning

confidence: 99%

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Mertan

Cheney

2023

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

show abstract

“…In a multitask setting, Powers et al [23] recently demonstrated that certain body plans suffer catastrophic forgetting, while others do not. It was hypothesized that a robot with the right morphology could in some cases alias separate tasks: certain designs are able to move in such a way that a seemingly different training instance converges sensorially to a familiar instance.…”

Section: Introductionmentioning

confidence: 99%

Morphology dictates learnability in neural controllers

Powers

Grindle

Kriegman

et al. 2020

The 2020 Conference on Artificial Life

Self Cite

View full text Add to dashboard Cite

Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments. Efforts to combat catastrophic forgetting reported in the literature to date have focused on how control systems can be updated more rapidly, hastening their adjustment from good initial settings to new environments, or more circumspectly, suppressing their ability to overfit to any one environment. When using robots, the environment includes the robot's own body, its shape and material properties, and how its actuators and sensors are distributed along its mechanical structure. Here we demonstrate for the first time how one such design decision (sensor placement) can alter the landscape of the loss function itself, either expanding or shrinking the weight manifolds containing suitable controllers for each individual task, thus increasing or decreasing their probability of overlap across tasks, and thus reducing or inducing the potential for catastrophic forgetting.

show abstract

“…Evolved robots have been transferred to reality (Ruud et al, 2016) although the reality gap remains a persistent issue (Stanton, 2018;Koos et al, 2010;Jakobi, 1998). While enhancing performance of systems is often the primary goal, one outstanding area is quantifying the impact that different components of a robotic system (Powers et al, 2018), or the underlying evolutionary algorithm (Dolson and Ofria, 2018), have on evolved systems.…”

Section: Introductionmentioning

confidence: 99%

The Limits of Lexicase Selection in an Evolutionary Robotics Task

Moore

Stanton

2019

The 2019 Conference on Artificial Life

View full text Add to dashboard Cite

Agents exhibiting generalized control are capable of solving a theme of related tasks, rather than a specific instance. Here, generalized control pertains to the locomotive capacity of quadrupedal animats, evaluated when climbing over walls of varying height to reach a target. In prior work, we showed that Lexicase selection is more effective than other evolutionary algorithms for this wall crossing task. Generalized controllers capable of crossing the majority of wall heights are discovered, even though Lexicase selection does not sample all possible environments per generation. In this work, we further constrain environmental sampling during evolution, examining the resilience of Lexicase to the impoverished conditions. Through restricting the range of samples at given points in time as well as fixing environmental exposure over fractions of evolutionary time, we attempt to increase the 'adjacency' of environmental samples, and report on the response of the Lexicase algorithm to the pressure of this reduced environmental diversity. Results indicate that Lexicase is robust, producing viable agents even in considerably challenging conditions. We also see a positive correlation between the number of tiebreak events that occur and the success of individuals in a population, except in the most limiting conditions. We argue that the increased number of tiebreaks is a response to local maxima, and the increased diversity resulting from random selection at this point, is a key driver of the resilience of the Lexicase algorithm. We also show that in extreme cases, this relationship breaks down. We conclude that tiebreaking is an important control mechanism in Lexicase operation, and that the breakdown in performance observed in extreme conditions indicates an inability of the tiebreak mechanism to function effectively where population diversity is unable to reflect environmental diversity.

show abstract

The effects of morphology and fitness on catastrophic interference

Cited by 4 publications

References 0 publications

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Morphology dictates learnability in neural controllers

The Limits of Lexicase Selection in an Evolutionary Robotics Task

Contact Info

Product

Resources

About