Dynamic Reward Shaping: Training a Robot by Voice

By Ana Cecilia Tenorio-González, Eduardo F. Morales, Luis Villaseñor-Pineda. 2010

97 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Mechanical Engineering

How researchers see this paper

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

In Artificial Intelligence

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Leveraging Human Guidance for Deep Reinforcement Learning Tasks (2019, background): “In contrast to policy shaping, reward shaping interprets human feedback as the value function or a human-speciﬁed reward function [Isbell et al. , 2001; Tenorio-Gonzalez et al. , 2010; Pilarski et al. , 2011].”
Interactive Learning from Policy-Dependent Human Feedback (2017, background): “Some research has also examined combining human feed-back with more traditional environmental rewards (Knox & Stone, 2010; Tenorio-Gonzalez et al., 2010; Clouse & Utgoff, 1992; Maclin et al., 2005).”
Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback (2017, background): “Reinforcement learning has become the de facto standard for incorporating this feedback across diverse tasks such as robot voice control (Tenorio-Gonzalez et al., 2010), myoelectric control (Pilarski et al.”
Reinforcement learning in robotic applications: a comprehensive survey (2021, unknown): “So, reward shaping techniques are developed for the learning of agent in complex robotics task (Ng et al. 1999; Thomaz and Breazeal 2008; Tenorio-Gonzalez et al. 2010).”
Human-robot cross-training: Computational formulation, modeling and evaluation of a human team training strategy (2013, methodology): “Under this formulation, the role of the robot is represented by the optimal policy π ∗ , whereas the robot’s knowledge of the role of the human co-worker is represented by the transition probabilities T .”
Policy Shaping: Integrating Human Feedback with Reinforcement Learning (2013, background): “This is the most common way human feedback has been applied to RL [1] [2] [3] [4] [5].”
Learning non-myopically from human-generated reward (2013, background): “This mapping to 1 and -1, though not infallible, is an intuitive choice that is similar to that of related works that explain their exact mappings [14, 13, 10, 11].”
Transfer Learning in Deep Reinforcement Learning: A Survey (2020, background): “[79], spoken dialogue systems [80], and question answering [81].”
DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback (2018, background): “…follows: 1) We precisely formulate the following more realistic human-in-the-loop RL settings: ( BINARY FEEDBACK , [9] Tenorio-Gonzalez et al. 2010 [10] (voice) Pilarski et al. 2011 [11] Grifﬁth et al. 2013 [12] MacGlashan et al. 2017 [13] Arumugam et al. 2018 [14] Warnel et al. 2018 [15] Ours…”
Reinforcement learning from simultaneous human and MDP reward (2012, methodology): “[18] expanded this learning algorithm, additionally using human demonstrations.”
Improved human–robot team performance through cross-training, an approach inspired by human team training practices (2015, background): “, 2011) and within an interactive learning framework wherein the user administers rewards to a robot through verbal commands (Tenorio-Gonzalez et al., 2010).”