The Playground Experiment: Task-Independent Development of a Curious Robot

By Pierre-Yves Oudeyer, Verena Vanessa Hafner, Andrew Whyte. 2005

114 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

Guest Editorial Active Learning and Intrinsically Motivated Exploration in Robots: Advances and Challenges (2010, background): “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”
From hardware and software to kernels and envelopes: a concept shift for robotics, developmental psychology, and brain sciences (2011, background): “Details of one version of this progress-driven kernel can be found in (Oudeyer et al., 2007) and also in the appendix of this chapter (see also earlier version in (Kaplan and Oudeyer, 2003; Oudeyer et al., 2005)).”
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 opti mal 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 Oudeye”
Reinforcement learning of hierarchical skills on the sony aibo robot (2005, background): “Greater eventual success at this would allow progress on the important goal of making broadly competent agents (see [6] for a related effort).”
Abandoning Objectives: Evolution Through the Search for Novelty Alone (2011, methodology): “…metric based on algorithmic information theory, and Evolutionary Computation Volume 19, Number 2 213 research in adaptive curiosity in developmental robotics may also provide insight into defining appropriate characterizations of behavior (Kaplan and Hafner, 2006; Oudeyer et al., 2005, 2007).”
The strategic student approach for life-long exploration and learning (2012, background): “When viewed in the SSP setting, each topic can be either a local predictive forward model [20], [43], an option [22], or a region in a parameterized goal/option space [11], i.”
Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges (2010, background): “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”
Discovering communication (2006, background): “A major challenge for this research area is to design intrinsic motivation systems that would permit some form of open-ended task-independent organized development (Weng et al. 2001, Oudeyer et al. 2005a).”