This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 1…

Subfields: Reinforcement Learning, Meta & Continual Learning

Citations in the corpus

• Recurrent World Models Facilitate Policy Evolution (2018, background): “An exciting research direction is to look at ways to incorporate artificial curiosity and intrinsic motivation [61, 64, 77, 80, 81] and information seeking [23, 86] abilities in an agent to encourage novel exploration [47].”
• Unifying Count-Based Exploration and Intrinsic Motivation (2016, background): “This guidance can be summarized as “explore what surprises you”.”
• Recurrent Environment Simulators (2017, background): “…can empower agent-based systems with a vast array of abilities, including counterfactual reasoning (Pearl, 2009), intuitive physical reasoning (McCloskey, 1983), model-based exploration, episodic control (Lengyel & Dayan, 2008), intrinsic motivation (Oudeyer et al., 2007), and hierarchical control.”
• Continual Lifelong Learning with Neural Networks: A Review (2018, background): “Pallier et al. (2003) studied the word recognition abilities of Korean-born adults whose language environment shifted completely from Korean to French after being adopted between the ages of 3 and 8 by French families.”
• Weight Agnostic Neural Networks (2019, background): “…single WANN capable of encoding many different useful tasks in its environment, one might consider developing a WANN with a strong intrinsic bias for intrinsic motivation [82, 84, 94], and continuously optimize its architecture to perform well at pursuing novelty in an open-ended environment [60].”
• World Models (2018, background): “…direction is to look at ways to incorporate artificial curiosity and intrinsic motivation (Schmidhu-ber, 2010; 2006; 1991b; Pathak et al., 2017; Oudeyer et al., 2007) and information seeking (Schmidhuber et al., 1994; Gottlieb et al., 2013) abilities in an agent to encourage novel exploration…”
• Curiosity-Driven Exploration by Self-Supervised Prediction (2017, background): “Curiosity-driven exploration is a well studied topic in the reinforcement learning literature and a good summary can be found in (Oudeyer & Kaplan, 2009; Oudeyer et al., 2007).”
• Automated Curriculum Learning for Neural Networks (2017, background): “We propose to instead treat the decision about which task to study next as a stochastic policy, continuously adapted to optimise some notion of what Oudeyer et al. (2007) termed learning progress .”
• Exploration by Random Network Distillation (2018, methodology): “To avoid the undesirable factors 2 and 3, methods such as those by Schmidhuber (1991a); Oudeyer et al. (2007); Lopes et al. (2012); Achiam & Sastry (2017) instead use a measurement of how much the prediction model improves upon seeing a new datapoint.”
• Variational Bayesian Reinforcement Learning with Regret Bounds (2018, methodology): “In the non-tabular case methods that estimate the pseudo-count have proven successful in some instances, indicating a possibility of combining K-learning with pseudo-counts in a deep RL setting [94, 11, 97, 80, 13, 79].”
• Count-Based Exploration with Neural Density Models (2017, methodology): “, 2012), where they measure an agent’s learning progress (Oudeyer et al., 2007).”
• Continual Learning for Robotics (2019, background): “, 2001; Smith and Gasser, 2005), intrinsic motivation or curiosity (Oudeyer et al., 2007; Schmidhuber, 2010) as in (Forestier et al.”
• Dynamics-Aware Unsupervised Discovery of Skills (2019, methodology): “Another line of work that is conceptually close to our method copes with intrinsic motivation [51, 52, 58] which is used to drive the agent’s exploration.”
• Learning to Play with Intrinsically-Motivated Self-Aware Agents (2018, background): “One approach may be improving our formulation of curiosity from the simple adversarial concept to include additional notions of intrinsic motivation such as learning progress [33, 34, 38].”
• Curiosity Driven Exploration of Learned Disentangled Goal Spaces (2018, background): “Unsupervised learning approaches could then build coarse categories distinguishing the body, controllable objects, other animate agents, and uncontrollable objects as entities with different learning progress profiles [28].”
• Zero-Shot Visual Imitation (2018, methodology): “Furthermore, using navigation experiments in VizDoom environment, we show that (GSP) learned using curiosity-driven exploration (Oudeyer et al., 2007; Pathak et al., 2017; Schmidhuber, 1991) can more accurately follow demonstrations as compared to using random exploration data for learning the GSP.”
• State Representation Learning for Control: An Overview (2018, background): “One way to incorporate exploration in SRL is to integrate curiosity or intrinsic motivations [Oudeyer et al., 2007] in the algorithm that collects data.”