Results 1 to 10 of about 1,154 (117)
PLoS Biology, 2020 While there is no doubt that social signals affect human reinforcement learning, there is still no consensus about how this process is computationally implemented.
Anis Najar +3 more
doaj +2 more sources
imitation: Clean Imitation Learning Implementations
CoRR, 2022 imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation learning algorithms and a preference comparison algorithm. The implementations have been benchmarked against previous results, and automated tests cover 98% of the code.
Adam Gleave +9 more
openaire +2 more sources
Co-imitation: Learning Design and Behaviour by Imitation
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a robot 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.
Chang Rajani +4 more
openaire +3 more sources
ACM Computing Surveys, 2017 Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing ...
Ahmed Hussein 0001 +3 more
openaire +3 more sources
CoRR, 2020 In analogy to compressed sensing, which allows sample-efficient signal reconstruction given prior knowledge of its sparsity in frequency domain, we propose to utilize policy simplicity (Occam's Razor) as a prior to enable sample-efficient imitation learning.
Nathan Zhao, Beicheng Lou
openaire +2 more sources
Imitation learning for task allocation [PDF]
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010 At the heart of multi-robot task allocation lies the ability to compare multiple options in order to select the best. In some domains this utility evaluation is not straightforward, for example due to complex and unmodeled underlying dynamics or an adversary in the environment. Explicitly modeling these extrinsic influences well enough so that they can
Felix Duvallet, Anthony Stentz
openaire +1 more source
Imitation Learning by Reinforcement Learning
CoRR, 2021 Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical analysis both certifies the recovery of expert reward and bounds the total variation distance between the expert and
openaire +3 more sources
Predictability of imitative learning trajectories [PDF]
Journal of Statistical Mechanics: Theory and Experiment, 2019 Abstract The fitness landscape metaphor plays a central role in the modeling of optimizing principles in many research fields, ranging from evolutionary biology, where it was first introduced, to management research. Here we consider the ensemble of trajectories of an imitative learning search, in which agents exchange information on ...
Paulo R. A. Campos, José F. Fontanari
openaire +3 more sources
Multimodal imitative learning and synchrony in cetaceans: A model for speech and singing evolution
Frontiers in Psychology, 2023 Multimodal imitation of actions, gestures and vocal production is a hallmark of the evolution of human communication, as both, vocal learning and visual-gestural imitation, were crucial factors that facilitated the evolution of speech and singing ...
José Zamorano-Abramson +6 more
doaj +1 more source
An Algorithmic Perspective on Imitation Learning [PDF]
Foundations and Trends® in Robotics, 2018 As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it.
Takayuki Osa +5 more
openaire +5 more sources