See Blockindiscussions, Blockinstats, Blockinand Blockinauthor Blockinprofiles Blockinfor Blockinthis Blockinpublication Training Blockina Blockinrobot Blockinvia Blockinhuman Blockinfeedback:…

Citations in the corpus

• Interactive Learning from Policy-Dependent Human Feedback (2017, methodology): “We chose TAMER as a comparison because, to our knowledge, it is the only HCRL algorithm with success on a similar platform [23].”
• Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces (2017, methodology): “This observation was recently made and exploited in a series of papers outlining the TAMER framework (Knox and Stone 2009; 2012; Knox, Stone, and Breazeal 2013; Knox and Stone 2015) (see Figure 1), in which it was shown that agents learning directly from non-expert human trainers can improve over…”
• Continual Learning for Affective Robotics: Why, What and How? (2020, background): “Interactive Reinforcement Learning (IRL) techniques, with the human in the loop [62]–[64], offer potent solutions for embedding such dynamic real-time”
• Learning something from nothing: Leveraging implicit human feedback strategies (2014, methodology): “Two common approaches are techniques based on reinforcement learning [15] of a reward function that assigns values to actions [8] and learning from demonstration [3] using demonstrations of behaviors.”
• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, methodology): “Finally, rather than using corrective demonstrations, the TAMER framework utilizes real-time numeric human feedback about the robot’s performance to correct and shape behavior [197].”
• A survey of robot learning from demonstrations for Human-Robot Collaboration (2017, background): “…Learning and considers a robot as an active partner that provides feedback to the human teacher during the collaboration phase, and then the feedback can be used for reducing uncertainty in terms of accomplishing to learn new tasks so that that learning process is able to become more efficient [16].”
• Robots That Use Language (2020, background): “A bottle consists of a bottle and a cap, and a person referencing “the bottle” may mean both, or they may say, “Grab the bottle and then turn the cap,”referring”
• Interactively shaping robot behaviour with unlabeled human instructions (2019, background): “Delivering evaluative feedback is an intuitive way for training a robot that presents some advantages over traditional RL reward functions, such as being more directly informative about the optimal behaviour and easier to implement [21].”
• The EMPATHIC Framework for Task Learning from Implicit Human Feedback (2020, background): “We view learning from implicit human feedback (LIHF) as complementary to learning from explicit human teaching, which might take the form of demonstrations [1], evaluative feedback [2, 3], or other communicative modalities [4, 5, 6, 7, 8].”