A Teaching Method for Reinforcement Learning

By J. Clouse, Paul E. Utgoff. 1992

How researchers see this paper

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

Citations in the corpus

Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation (2018, methodology): “ combing SL and RL utilize expert behaviors to accelerate reinforcement learning and avoid the risks of actions. Common examples are imitation learning [1, 12, 19, 28, 44] and supervised actor-critic [5, 6, 10]. Given the samples of expert trajectories, imitation learning requires th skill of estima”
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).”
Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer (2004, background): “The advice may suggest an action to be taken immediately ( Clouse & Utgoff 1992 ), or it may contain explicit con-”
A comprehensive survey on safe reinforcement learning (2015, background): “Additionally, the nature of the advice can have various forms: a single action that the learner carries out at that time (Clouse and Utgoff, 1992; Clouse, 1997; García and Fernández, 2012); a complete sequence of actions that the learner agent replays internally (Lin, 1992; Driessens and Džeroski,…”
Bootstrapping intrinsically motivated learning with human demonstration (2011, background): “xplores on his own to learn tasks or skills beyond what it has observed with a human. Many prior works have given a human trainer control of the reinforcement learning reward [8], [9], provide advice [10], or tele-operate the agent during training [11]. However, the more dependent on the human the s”
A Review of Safe Reinforcement Learning: Methods, Theories, and Applications (2024, unknown): “Fromtheperspectiveofknowledgeutilization, somemethodsconsidersafetyintheRLexplorationprocessby leveragingexternalknowledge,e.g.,[34],[100],[101],[102], [103],[104],[105].”
Reinforcement learning with supervision by a stable controller (2004, methodology): “As mentioned above, the architecture shown in Figure 2 is similar to one suggested previously by Clouse and Utgoff [10] and by Benbrahim and Franklin [11].”
Bootstrapping Intrinsically Motivated Learning with Human Demonstrations (unknown): “Many prior works have given a human trainer control of the reinforcement learning reward [8], [9], provide advice [10], or tele-operate the agent during training [11].”
Teachable robots: Understanding human teaching behavior to build more effective robot learners (2008, methodology): “Conceptually, our modiﬁed version gives the algorithm a pre-action and post-action phase in order to incorporate the new guidance input.”
Reinforcement Learning: An Introduction (1998, methodology): “In 1961 and 1963 he described a simple trial-and-error learning system for learning how to play tic-tac-toe (or naughts and crosses) called MENACE (for Matchbox Educable Naughts and Crosses Engine). It consisted of a matchbox for each possible game position, each matchbox containing a number of colo”
Interactively shaping robot behaviour with unlabeled human instructions (2019, methodology): “In [7], instructions are integrated into an RL algorithm by positively reinforcing the proposed action.”