Evolving virtual creatures

By Karl Sims. 1994

How researchers see this paper

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

In Evolutionary Computation

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Many RNN evolvers have been proposed (e.g., Miller et al., 1989; Wieland, 1991; Cliff et al., 1993; Yao, 1993; Nolfi et al., 1994a; Sims, 1994; Yamauchi and Beer, 1994; Miglino et al., 1995; Moriarty, 1997; Pasemann et al., 1999; Juang, 2004; Whiteson, 2012).”
Hyperparameter Selection for Imitation Learning (2021, background): “Indeed, just as the reward-engineering problem leads to policies maximizing a reward in an unexpected way (Sims, 1994; Feldt, 1998; Ecoffet et al., 2021), selecting policies on the basis of an incautiously designed metric or of a biased human judgement can lead to biased policies (Henderson et al.,…”
Emergent Tool Use From Multi-Agent Autocurricula (2019, background): “Our work sees itself in the tradition of previous studies that showcase emergent complexity in simple physically grounded environments [11, 12, 13, 14]; the success in these settings inspires confidence that inducing autocurricula in physically grounded and open-ended environments could eventually e”
DeepMind Control Suite (2018, background): “2This phenomenon, sometimes known as Sims’ Law, was first articulated in (Sims, 1994): “Any bugs that allow energy leaks from non-conservation, or even round-off errors, will inevitably be discovered and exploited”.”
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities (2018, neutral): “In further virtual-creature experiments [126, 127], Karl Sims ʼ attempt to evolve swimming strategies resulted in new ways for evolution to cheat.”
Emergent Complexity via Multi-Agent Competition (2017, background): “Our work is also related to early work in the graphics community [Sims, 1994] on evolving creature morphology in varying environments using genetic algorithm and work in animation [Wampler et al., 2010] for adversarial games.”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1, except that C is now an FNN or RNN trained by evolutionary algorithms [200, 255, 105, 56, 68] applied to NNs [165, 321, 180, 259, 72, 90, 89, 110, 94], or by policy gradient methods [314, 315, 316, 274, 18, 1, 63, 128, 313, 210, 192, 191, 256, 85, 312, 190, 82, 93][245, Sec.”
One Big Net For Everything (2018, background): “Without a teacher, reward-maximizing programs of an RNN must be learned through repeated trial and error, e.g., through artiﬁcial evolution [39, 107, 83, 40, 16, 18, 103, 14, 89, 88] [76, Sec.”
Evolving 3D Morphology and Behavior by Competition (1994, methodology): “A different version of the system described here has also been used to generate virtual creatures by optimizing for specific defined behaviors such as swimming, walking, and following [22].”
Hormone-inspired adaptive communication and distributed control for CONRO self-reconfigurable robots (2002, background): “Karl Sims [38] has studied this question in details and developed a system for discovering the motion possibilities of different block structures.”
Challenges and Opportunities for Design, Simulation, and Fabrication of Soft Robots (2014, unknown): “method for representing spatial functions has been the compositional pattern producing network, 12 which can be used to describe robot morphologies by specifying the type of material as a function of spatial coordinates 2,4 (Fig.”
Evolving developing spiking neural networks (2005, background): “Some models include additional contextual information in each rule definition [32, 19, 18], so that phenotypic traits variations can be generated.”
dm_control: Software and Tasks for Continuous Control (2020, background): “6This phenomenon, known as Sims’ Law, was first articulated in (Sims, 1994): “Any bugs that allow energy leaks from non-conservation, or even round-off errors, will inevitably be discovered and exploited”.”
Reinforcement Learning Upside Down: Don't Predict Rewards - Just Map Them to Actions (2019, background): “RL is also very different from traditional black box optimization (BBO) [36, 57, 19, 9] such as neuroevolution [29, 59, 14, 12] which can be used to solve complex RL problems in partially observable environments [15] through iterative discovery of better and better parameters of an adaptive…”
Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding (2013, background): “Unshackling Evolution: Evolving Soft Robots with Multiple Materials and a Powerful Generative Encoding Nick Cheney, Robert MacCurdy, Jeff Clune*, Hod Lipson Creative Machines Lab, Cornell University Ithaca, New York, USA *Evolving AI Lab, University of Wyoming *Laramie, Wyoming, USA…”
Robust treatment of collisions, contact and friction for cloth animation (2002, background): “For example, [Sims 1994] switched between instantaneous impulses for high velocities and penalty spring forces for low velocities to treat his evolving articulated rigid body creatures.”
Reinforcement Learning for Improving Agent Design (2018, methodology): “In 1994, Karl Sims demonstrated that artiﬁcial evolution can produce novel morphology that resemble organisms observed in nature [59, 60].”