Search Results for author:
Found 21 papers, 4 papers with code
Three Dogmas of Reinforcement Learning
Modern reinforcement learning has been conditioned by at least three dogmas.
Exploring the hierarchical structure of human plans via program generation
Human behavior is often assumed to be hierarchically structured, made up of abstract actions that can be decomposed into concrete actions.
Structurally guided task decomposition in spatial navigation tasks
How are people able to plan so efficiently despite limited cognitive resources?
Bayesian Reinforcement Learning with Limited Cognitive Load
All biological and artificial agents must learn and make decisions given limits on their ability to process information.
Humans decompose tasks by trading off utility and computational cost
Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions.
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning
Throughout the cognitive-science literature, there is widespread agreement that decision-making agents operating in the real world do so under limited information-processing capabilities and without access to unbounded cognitive or computational resources.
Linguistic communication as (inverse) reward design
We then define a pragmatic listener which performs inverse reward design by jointly inferring the speaker's latent horizon and rewards.
On the Expressivity of Markov Reward
We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists.
Cognitive science as a source of forward and inverse models of human decisions for robotics and control
Those designing autonomous systems that interact with humans will invariably face questions about how humans think and make decisions.
Extending rational models of communication from beliefs to actions
Speakers communicate to influence their partner's beliefs and shape their actions.
People construct simplified mental representations to plan
We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting.
Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation
Nonetheless, a teacher and learner may not always experience or attend to the same aspects of the environment.
Learning Rewards from Linguistic Feedback
The sentiment models outperform the inference network, with the "pragmatic" model approaching human performance.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners
To solve the machine teaching optimization problem, we use a deep learning approximation method which simulates learners in the environment and learns to predict how feedback affects the learner's internal states.
Resource-rational Task Decomposition to Minimize Planning Costs
That is, rather than planning over a monolithic representation of a task, they decompose the task into simpler subtasks and then plan to accomplish those.
The Efficiency of Human Cognition Reflects Planned Information Processing
Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions.
On the Utility of Learning about Humans for Human-AI Coordination
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves.
The Computational Structure of Unintentional Meaning
Speech-acts can have literal meaning as well as pragmatic meaning, but these both involve consequences typically intended by a speaker.
Learning Task Specifications from Demonstrations
In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications.
Interactive Learning from Policy-Dependent Human Feedback
This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback.
Showing versus doing: Teaching by demonstration
Stark differences arise when demonstrators are intentionally teaching a task versus simply performing a task.
