Nov 28, 2022
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior by giving demonstrations that best disambiguate the goal they want to demonstrate. Analogously, human learners excel at pragmatically inferring the intent of the teacher, facilitating communication between the two agents. These mechanisms are critical in the few demonstrations regime, where inferring the goal is more difficult. In this paper, we implement pedagogy and pragmatism mechanisms by leveraging a Bayesian model of goal inference from demonstrations. We highlight the benefits of this model in multi-goal teacher-learner setups with two artificial agents that learn with goal-conditioned Reinforcement Learning. We show that combining a pedagogical teacher and a pragmatic learner results in faster learning and reduced goal ambiguity over standard learning from demonstrations, especially in the few demonstrations regime.Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior by giving demonstrations that best disambiguate the goal they want to demonstrate. Analogously, human learners excel at pragmatically inferring the intent of the teacher, facilitating communication between the two agents. These mechanisms are critical in the f…
Account · 953 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Hao Xiong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Ossi Räisä, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Yiyun Luo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Rujie Zhong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%