SC-EUNE - Surprise/Curiosity-based Exploration of UNcertain and UNknown Environments
نویسندگان
چکیده
This paper describes the architecture of SC-EUNE, a simulated artificial agent that explores uncertain and unknown environments guided by forms of surprise and/or curiosity. Besides describing the environment where it acts, we present the following components of its architecture: percepts, actions, goals, memory, surprise and curiosity generation, and deliberative reasoning/decision-making.
منابع مشابه
Modeling Forms of Surprise in an Artificial Agent
Mainly rooted in the cognitive-psychoevolutionary model of surprise proposed by the research group of the University of Bielefeld (Meyer, Reisenzein, Schützwohl, etc.), the computational model of surprise described in this paper relies on the assumption that surprise-eliciting events initiate a series of mental processes that begin with the appraisal of unexpectedness, continue with the interru...
متن کاملThe practical advantage of surprise-based agents
We argue that taking surprise into account in the artificial agents’s reasoning may have advantageous implications in various situations. Relying on theoretical and empirical evidence, our arguments are supported by the application of surprise-based agents to three different domains, namely exploration of unknown environments, divergent production and evaluation of creative products, and select...
متن کاملModeling curiosity for virtual learning companions
Curiosity is an emotional motivation that drives knowledge acquisition in learning context. Studies have shown that curiosity positively influences social learning and a peer learner’s curiosity may elicit the curiosity of other learners. Hence, modeling curiosity in learning companions may improve human learners’ learning experience in virtual environments. However, curiosity has not been expl...
متن کاملIntegrating Planning, Creativity and Exploration in Motivational Agents
Although, planning and exploration of unknown environments has been previously addressed in multi-agent environments, we believe that in addition to these activities, agents may also benefit from exhibiting creativity so that they are able to imagine or invent new things (objects) that may be helpful or simply pleasant for the agents that inhabit the environment. Psychological and neuroscience ...
متن کاملCuriosity-Driven Exploration with Planning Trajectories
Reinforcement learning (RL) agents can reduce learning time dramatically by planning with learned predictive models. Such planning agents learn to improve their actions using planning trajectories, sequences of imagined interactions with the environment. However, planning agents are not intrinsically driven to improve their predictive models, which is a necessity in complex environments. This p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000