A Agent Environment StatesActions Rewards Critic B Agent Internal Environment Rewards Critic External Environment Sensations StatesDecisions Actions " Organism " Figure 1

By Andrew Barto, Satinder Singh, Nuttapong Chentanez. 2004

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Learning Parameterized Skills (2012, background): “, [5, 63, 4], where intrinsic motivation signals are used (for the first time, to the best of our knowledge) to autonomously identify and construct a set of skills.”
Deep learning in neural networks: An overview (2014, methodology): “While HRL frameworks such as Feudal RL (Dayan and Hinton, 1993) and options (Sutton et al., 1999b; Barto et al., 2004; Singh et al., 2005) do not directly address the problem of automatic subgoal discovery, HQ-learning (Wiering and Schmidhuber, 1998a) automatically decomposes POMDPs (Sec.”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “While HRL frameworks such as Feudal RL [48] and options [275, 16, 261] do not directly address the problem of automatic subgoal discovery, HQ-Learning [309] automatically decomposes problems in partially observable environments into sequences of simpler subtasks that can be solved by memoryless poli”
Loss is its own Reward: Self-Supervision for Reinforcement Learning (2016, background): “Intrinsic rewards are intended to scaffold skill learning, aid exploration, or otherwise guide the policy to improve (Barto et al., 2004; Chentanez et al., 2004).”
What is Intrinsic Motivation? A Typology of Computational Approaches (2007, background): “This fi gure is inspired from Barto et al. (2004).”
Hierarchically organized behavior and its neural foundations: A reinforcement-learning perspective (2008, background): “Instead of learning from extrinsically provided rewards, the agent learns from intrinsic rewards generated by built-in mechanisms that identify subgoals—states or situations that have the property that skills capable of achieving them are likely to be useful in many different future tasks ( Barto, S”
Bootstrapping intrinsically motivated learning with human demonstration (2011, background): “they experience intrinsically. These mechanisms have been shown crucial for humans to autonomously learn and discover new capabilities [14]–[16]. This inspired the creation of fully autonomous robots [17]–[22] with meta-exploration mechanisms monitoring the evolution of learning performances of the ”
Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective (2010, background): “2 Barto et al. [3] used the term intrinsic reward to refer to rewards that produce analogs of intrinsic motivation in RL agents, and extrinsic reward to refer to rewards that define a specific task or rewarding outcome as in standard RL applications.”
Where Do Rewards Come From (2009, methodology): “Figure 1: Agent-environment interactions in reinforcement learning; adapted from Barto et al. (2004). See text for discussion.”
Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints (2013, background): “…learning and option theory, and more generally approaches to cumulative learning, and the reader is referred to the following articles for an overview of those techniques (Bakker and Schmidhuber, 2004; Barto et al., 2004; Ring, 1994; Sutton et al., 1999; Wiering and Schmidhuber, 1997).”
Active Learning and Intrinsically Motivated Exploration in Robots : Advances and Challenges (2010, background): “Two 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): “Skill learning can be made more explicit by identifying learned skills (Barto et al., 2004) within the option framework (Sutton et al., 1999).”
The challenges of joint attention (2006, background): “Barto, Singh and Chentanez have recently illustrated in a simple environment how options could be used to develop a hierarchical collection of skills (Barto et al., 2004).”
From hardware and software to kernels and envelopes: a concept shift for robotics, developmental psychology, and brain sciences (2011, methodology): “The term “intrinsically motivated reinforcement learning” has been used by Barto in this context (Barto et al., 2004).”
Intrinsically Motivated Reinforcement Learning: A Promising Framework for Developmental Robot Learning (2005, methodology): “Barto, Singh, and Chentanez ( Barto, Singh, & Chentanez 2004; Singh, Barto, & Chentanez 2004) have recently presented an algorithm for intrinsically motivated reinforcement learning that strives to achieve broad competence in an environment in a tasknonspecific manner by incorporating internal rewa”
2009 Ieee 8th International Conference on Development and Learning (background): “Machine learning researchers have proposed that such mechanism might be crucial for self-organizing developmental trajectories as well as for guiding the learning of general and reusable skills in machines and robots [9] [10].”
Skill Characterization Based on Betweenness (2008, background): “We assume that the agent’s interaction with its environment may be represented as a Markov Decision Process (MDP).”