Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces
نویسندگان
چکیده
Intrinsic motivations are mechanisms that guide curiosity-driven exploration (Berlyne, 1965). They have been proposed to be crucial for self-organizing developmental trajectories (Oudeyer et al. , 2007) as well as for guiding the learning of general and reusable skills (Barto et al., 2005). Here, we argue that they can be considered as “active learning” algorithms, and show that some of them also allow for very efficient learning in unprepared sensorimotor spaces, outperforming existing active learning algorithms.
منابع مشابه
Intrinsically Motivated Exploration for Developmental and Active Sensorimotor Learning
Intrinsic motivation is a central mechanism that guides spontaneous exploration and learning in humans. It fosters incremental and progressive sensorimotor and cognitive development by pushing exploration of activities of intermediate complexity given the current state of capabilities. This chapter presents and studies two computational intrinsic motivation systems that share similarities with ...
متن کاملIntrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
Intrinsically motivated spontaneous exploration is a key enabler of autonomous lifelong learning in human children. It allows them to discover and acquire large repertoires of skills through self-generation, self-selection, self-ordering and self-experimentation of learning goals. We present the unsupervised multi-goal reinforcement learning formal framework as well as an algorithmic approach c...
متن کاملActive learning of inverse models with intrinsically motivated goal exploration in robots
We introduce the Self-Adaptive Goal Generation Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsically motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distributio...
متن کاملUnsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments. These exploration algorithms have been shown to allow real world robots to acquire skills such as tool use in high-dimensional continuous state and action spaces. However, they have so far assumed that self-generated goals are sampl...
متن کاملIntrisically Motivated Goal Space Creation for Autonomous Goal-Directed Exploration in High-Dimensional Unbounded Sensorimotor Spaces
Today’s robotic systems are given increasingly complex tasks in an increasing variety of situations such as object or social interaction. Many of those situations cannot be anticipated at design time : autonomous learning capacities are needed to adapt to novel, unexpected conditions. Yet, because of their complex bodies and multiple sensors, robots face highly-dimensional, unbounded, continuou...
متن کامل