Results 11 to 20 of about 11,612 (263)
Delayed Reinforcement Learning by Imitation
CoRR, 2022 When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail. In this paper, we propose a simple yet new and efficient solution to this problem. We assume that, in the undelayed environment, an efficient policy is known or can be easily learned, but the task may suffer from delays in practice and we thus ...
Pierre Liotet +3 more
openaire +5 more sources
Computer Aided Design of Self-Learning Robotic System using Imitation Learning [PDF]
, 2022 Artificial intelligence (AI), imitation learning, big data, cloud and distributed computing, robotics cells, and information communication technology, are some of the key tools and elements of the future digital and smart manufacturing facility.
Wood, P., Jadeja, Y., Shafik, M.
core +1 more source
An Automated Driving Strategy Generating Method Based on WGAIL–DDPG
International Journal of Applied Mathematics and Computer Science, 2021 Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper proposes an automated driving decision-making method based on the Wasserstein generative adversarial imitation learning–deep ...
Zhang Mingheng +5 more
doaj +1 more source
Hierarchical Learning Approach for One-shot Action Imitation in Humanoid Robots [PDF]
, 2010 16/01/13 meb. pre-print version, OK to pub.We consider the issue of segmenting an action in the learning phase into a logical set of smaller primitives in order to construct a generative model for imitation learning using a hierarchical approach.
Yan Wu +3 more
core +1 more source
Imitation-theory and experimental evidence [PDF]
, 2003 We introduce a generalized theoretical approach to study imitation and subject it to rigorous experimental testing. In our theoretical analysis we find that the different predictions of previous imitation models are due to different informational ...
Oechssler, J. +8 more
core +1 more source
Imitation Learning with Sinkhorn Distances
, 2023 Published as a conference paper at ECML PKDD ...
Papagiannis, Georgios, Li, Yunpeng
openaire +3 more sources
IMITATION STRATEGIES FOR SME’S LEARNING PROCESS TOWARDS INNOVATION STRATEGIES
APMBA (Asia Pacific Management and Business Application), 2013 Imitation is actually a part of innovation strategy, the learning strategies to enter the market. It can be a stepping stone for SME”s in developing countries to innovate and to create a knowledge base to lower the innovation cost.
Rina Sulistiyani +3 more
doaj +1 more source
CoRR, 2018 This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration.
Junhyuk Oh +3 more
openaire +3 more sources
Imitation Learning for Locomotion and Manipulation [PDF]
2007 7th IEEE-RAS International Conference on Humanoid Robots, 2007 Decision making in robotics often involves computing an optimal action for a given state, where the space of actions under consideration can potentially be large and state dependent. Many of these decision making problems can be naturally formalized in the multiclass classification framework, where actions are regarded as labels for states.
Nathan D. Ratliff +2 more
openaire +1 more source
Acquisition of automatic imitation is sensitive to sensorimotor contingency [PDF]
, 2010 The associative sequence learning model proposes that the development of the mirror system depends on the same mechanisms of associative learning that mediate Pavlovian and instrumental conditioning. To test this model, two experiments used the reduction
Heyes, C. +17 more
core +1 more source