Novelty and Reinforcement Learning in the Value System of Developmental Robots

By Xiao Huang, John Weng. 2002

156 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “…Whitman and Atkeson (2010) Progressive tasks Asada et al. (1996) and Randløv and Alstrøm (1998) Directed exploration with prior knowledge Approach Employed by… Directed exploration Huang and Weng (2002), Kroemer et al. (2010), and Pendrith (1999) balls to a precise location on the opponent’s court.”
Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “…havebeenproposedindevelopmentalrobotics,suchasthosebased on the psychological concept of intrinsic motivations [54,46,55] which relate to mechanisms that drive a learning agent to perform different activities for their own sake, without requiring any exter-nal reward [39,33,56–61,41 ,62 –65 ].”
What is Intrinsic Motivation? A Typology of Computational Approaches (2007, background): “…particular models of intrinsic motivation have already been developed in the literature (e.g., Barto and Simsek, 2005; Bonarini et al., 2006; Huang and Weng, 2002; Kaplan and Oudeyer, 2003; Marshall et al., 2004; Merrick and Maher, 2008; Oudeyer et al., 2005, 2007; Schmidhuber, 1991; Thrun,…”
Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot (2007, background): “Consequently, researchers in both machine learning [10][11] and developmental robotics [12][13][14] started to investigate systems with a twofold learning process.”
Intrinsically Motivated Reinforcement Learning: A Promising Framework for Developmental Robot Learning (2005, background): “There are many possibilities for the source of intrinsic motivation, including surprise, novelty (Huang & Weng 2002), or “learning progress” (Kaplan & Oudeyer 2004).”
The challenges of joint attention (2006, background): “A major trend in these models is to study the behavior of systems driven by some sort of artificial curiosity or search for optimal experiments (Fedorov, 1972; Schmidhuber, 1991; Cohn et al., 1994; Thrun, 1995; Herrmann et al., 2000; Huang and Weng, 2002; Kaplan and Oudeyer, 2003; Kaplan and Oudey”
Evolving Childhood's Length and Learning Parameters in an Intrinsically Motivated Reinforcement Learning Robot (2007, background): “Recently, in both the machine learning and the developmental/epigenetic robotics communities, a number of proposals have been put forward for solving such limitations by relying on autonomous robot development (Kaplan and Oudeyer, 2003; Schmidhuber, 1991; Weng et al., 2001; Huang and Weng, 2002; Mar”
Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges (2010, background): “…communities of researchers, the first one in reinforcement learning [9], [19], [23], [24], [42], the second one in developmental robotics [7], [20], [43]–[45], formalized, implemented, and experimented several mechanisms based on the concept of intrinsic motivation (sometimes called…”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, background): “What was possibly the ﬁrst AC-like implementation to run on hardware (Huang and Weng, 2002) rotated the head of the SAIL robot back and forth.”
Ieee Transactions on Evolutionary Computation Intrinsic Motivation Systems for Autonomous Mental Development (unknown): “In the first group (e.g. [18]; [15]; [20], [21]) robots directly use the error predicted by metaM to choose which action to do 1 .”
Intrinsically motivated hierarchical manipulation (2008, background): “Intrinsically rewarding mechanisms to motivate skill acquisition has also been applied in robot and reinforcement learning systems [3], [9].”
GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning (2016, background): “that tries to anticipate the effects of the actions of the artificial system in the environment [10], [31], [43], [57], [60].”
Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints (2013, background): “, Dayan and Belleine 2002; Doya 2002), and developmental robotics (e.g., Baldassarre and Mirolli 2012; Baranes and Oudeyer 2009; Blank et al. 2002; Hart and Grupen 2008; Huang and Weng 2002; Merrick 2012; Oudeyer and Kaplan 2007; Oudeyer et al. 2007; Schembri et al. 2007a; Schmidhuber 2006, 2010).”
An Emergent Framework For Self-Motivation In Developmental Robotics (2004, background): “A more recent version of SAIL employs a reinforcement signal that is the weighted sum of both external reinforcement and an internal measure of novelty [9].”
The Playground Experiment: Task-Independent Development of a Curious Robot (2005, background): “The first integrated view of developmental robotics that incorporated a proposal for a novelty drive was described by Weng and colleagues ((Weng 2002); ( Huang & Weng 2002 )).”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, unknown): “To address these shortcomings, exploration strategies based on the psychological concept of intrinsic motivation [58, 283] have used metrics such as novelty [167, 27, 144, 98, 50], uncertainty [259], and empowerment [266] to diversify”