Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLiteral or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
77
0
0.0
(
0
)
Added by
Smitha Milli
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
It is incredibly easy for a system designer to misspecify the objective for an autonomous system (robot), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people have an interest in the robot performing well, and will thus behave pedagogically, choosing actions that are informative to the robot. In turn, robots benefit from interpreting the behavior by accounting for this pedagogy. In this work, we focus on misspecification: we argue that robots might not know whether people are being pedagogic or literal and that it is important to ask which assumption is safer to make. We cast objective learning into the more general form of a common-payoff game between the robot and human, and prove that in any such game literal interpretation is more robust to misspecification. Experiments with human data support our theoretical results and point to the sensitivity of the pedagogic assumption.
rate research
Read More
Multi-objective controller synthesis concerns the problem of computing an optimal controller subject to multiple (possibly conflicting) objective properties. The relative importance of objectives is often specified by human decision-makers. However, there is inherent uncertainty in human preferences (e.g., due to different preference elicitation methods). In this paper, we formalize the notion of uncertain human preferences and present a novel approach that accounts for uncertain human preferences in the multi-objective controller synthesis for Markov decision processes (MDPs). Our approach is based on mixed-integer linear programming (MILP) and synthesizes a sound, optimally permissive multi-strategy with respect to a multi-objective property and an uncertain set of human preferences. Experimental results on a range of large case studies show that our MILP-based approach is feasible and scalable to synthesize sound, optimally permissive multi-strategies with varying MDP model sizes and uncertainty levels of human preferences. Evaluation via an online user study also demonstrates the quality and benefits of synthesized (multi-)strategies.
Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the humans desired objective already exists within the robots hypothesis space. In reality, this assumption is often inaccurate: there will always be situations where the person might care about aspects of the task that the robot does not know about. Without this knowledge, the robot cannot infer the correct objective. Hence, when the robots hypothesis space is misspecified, even methods that keep track of uncertainty over the objective fail because they reason about which hypothesis might be correct, and not whether any of the hypotheses are correct. In this paper, we posit that the robot should reason explicitly about how well it can explain human inputs given its hypothesis space and use that situational confidence to inform how it should incorporate human input. We demonstrate our method on a 7 degree-of-freedom robot manipulator in learning from two important types of human input: demonstrations of manipulation tasks, and physical corrections during the robots task execution.
As more and more robots are envisioned to cooperate with humans sharing the same space, it is desired for robots to be able to predict others trajectories to navigate in a safe and self-explanatory way. We propose a Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC). A set of experiments carried out on the human trajectory prediction problem shows that our model performs comparably to the state of the art and outperforms in some cases. More importantly, the proposed approach unveils the obscurity in the previous use of a pooling layer, presenting a way to intuitively explain the decision-making process.
Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of the model being learned. The reason is that the machine illustrates its beliefs by predicting and explaining the labels of the query instances: if the machine is unaware of its own mistakes, it may end up choosing queries on which it performs artificially well. This biases the narrative presented by the machine to the user.We address this narrative bias by introducing explanatory guided learning, a novel interactive learning strategy in which: i) the supervisor is in charge of choosing the query instances, while ii) the machine uses global explanations to illustrate its overall behavior and to guide the supervisor toward choosing challenging, informative instances. This strategy retains the key advantages of explanatory interaction while avoiding narrative bias and compares favorably to active learning in terms of sample complexity. An initial empirical evaluation with a clustering-based prototype highlights the promise of our approach.
Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could it learn it. For instance, when will the robot have a confident estimate in a nearby humans goal? Or, what parameter initializations guarantee that the robot can learn the humans preferences in a finite number of observations? To answer such analysis questions, our key idea is to model the robots learning algorithm as a dynamical system where the state is the current model parameter estimate and the control is the human data the robot observes. This enables us to leverage tools from reachability analysis and optimal control to compute the set of hypotheses the robot could learn in finite time, as well as the worst and best-case time it takes to learn them. We demonstrate the utility of our analysis tool in four human-robot domains, including autonomous driving and indoor navigation.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
