Method and system for interactive imitation learning in video games

• Main Authors: Juliani, Jr., Arthur William, Mattar, Mohamed Marwan A
• Format: Patent
• Language: English
• Published: 28.06.2022
• Subjects: AMUSEMENTS; CALCULATING; CARD, BOARD, OR ROULETTE GAMES; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; GAMES; GAMES NOT OTHERWISE PROVIDED FOR; HUMAN NECESSITIES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; PHYSICS; SPORTS; VIDEO GAMES

In example embodiments, a method of interactive imitation learning method is disclosed. An input is received from an input device. The input includes data describing a first set of example actions defining a behavior for a virtual character. Inverse reinforcement learning is used to estimate a reward function for the set of example actions. The reward function and the set of example actions is used as input to a reinforcement learning model to train a machine learning agent to mimic the behavior in a training environment. Based on a measure of failure of the training of the machine learning agent reaching a threshold, the training of the machine learning agent is paused to request a second set of example actions from the input device. The second set of example actions is used in addition to the first set of example actions to estimate a new reward function.