Abstract: The present disclosure may provide parameterized hyperparameter partitioning in consideration of balance in partition size while preserving a property of a hypergraph necessary to apply deep reinforcement learning by reducing the large-size hypergraph, and may reduce the computational amount and capacity of an artificial neural network by reducing a graph.

Abstract: Disclosed are an apparatus and a method for reinforcement learning based on a user learning environment in semiconductor design. According to the present disclosure, a user may configure a learning environment in semiconductor design and may determine optimal positions of semiconductor elements and standard cells through reinforcement learning using simulation, and reinforcement learning may be performed based on the learning environment configured by the user, thereby automatically determining optimized semiconductor element positions in various environments.

Abstract: Disclosed are a reinforcement learning device and method using a conditional episode configuration. The present invention imparts conditions on individual decision making, and terminates an episode if the imparted conditions are not met, thereby maximizing the total sum of rewards reflecting the current values. Accordingly, reinforcement learning can be easily applied even to problems using a non-continuous state.

Abstract: Disclosed are an apparatus and a method for reinforcement learning for semiconductor element position optimization based on semiconductor design data. According to the present disclosure, a learning environment may be constructed based on a user's semiconductor design data such that optimal positions of semiconductor elements are provided during a semiconductor design process through reinforcement learning using simulation.

Abstract: Disclosed is a deep reinforcement learning apparatus and method for a pick-and-place system. According to the present disclosure, a simulation learning framework is configured to apply reinforcement learning to make pick-and-place decisions using a robot operating system (ROS) in a real-time environment, thereby generating stable path motion that meets various hardware and real-time constraints.

Abstract: A vehicle including a drive wheel and a set of pedals coupled to the drive wheel. The vehicle includes a steering shaft connected to two front wheels. The vehicle includes a front load unit that may be engaged to be supported on a subframe between the two front wheels, the load unit being convertible between passenger seat and cargo storage configurations. In an aspect, the front load unit includes a horizontal load area and a substantially vertical shell forming a back wall and side walls. The front load unit may include a foot support hingedly mounted to the horizontal load area and pivotable between a lower position when the front load unit is configured as a passenger seat and a raised position parallel to the horizontal load area when the front load unit is configured as a cargo storage area.

Abstract: Disclosed are generative adversarial network-based classification system and method. The present invention can generate missing data as missing data imputation values similar to real data using a generative adversarial network (GAN), thus allowing the overall quality of the data to be improved, and allowing training with labeled data sets with labels, as well as irregular data sets such as non-labeled data sets without labels.

Abstract: Disclosed is a decision-making agent having a hierarchical structure. The present invention allows a user without knowledge about reinforcement learning to learn by easily setting and applying core factors of the reinforcement learning to business problems.

Abstract: A vehicle including a drive wheel and a set of pedals coupled to the drive wheel. The vehicle includes a steering shaft connected to two front wheels. The vehicle includes a front load unit that may be engaged to be supported on a subframe between the two front wheels, the load unit being convertible between passenger seat and cargo storage configurations. In an aspect, the front load unit includes a horizontal load area and a substantially vertical shell forming a back wall and side walls. The front load unit may include a foot support hingedly mounted to the horizontal load area and pivotable between a lower position when the front load unit is configured as a passenger seat and a raised position parallel to the horizontal load area when the front load unit is configured as a cargo storage area.

Abstract: Disclosed is a diffuser controller for tidal stream power generation, for use in a tidal stream power generator installed under water to generate electricity using a tidal stream. The diffuser controller includes: a turbine configured to be rotated by the tidal stream; a diffuser which is formed with an inlet through which a fluid flows into the diffuser and an outlet through which the fluid flows out from the diffuser, the turbine being fixed inside the diffuser and a rear foil being rotatably installed in the outlet; and a control unit configured to adjust an rotating angle of the rear foil depending on a direction or velocity of the tidal stream. The diffuser is configured to be rotatable.