Search Results for author:
Found 22 papers, 4 papers with code
Social Contract AI: Aligning AI Assistants with Implicit Group Norms
We explore the idea of aligning an AI assistant by inverting a model of users' (unknown) preferences from observed interactions.
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents.
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models
In this work, we adopt a novel perspective wherein a pre-trained language model is itself simultaneously a policy, reward function, and transition function.
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.
Inclusive Artificial Intelligence
Prevailing methods for assessing and comparing generative AIs incentivize responses that serve a hypothetical representative individual.
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.
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
The Bayes-Adaptive Markov Decision Process (BAMDP) formalism pursues the Bayes-optimal solution to the exploration-exploitation trade-off in reinforcement learning.
Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning
The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment.
Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
To address this problem, we introduce an algorithm that, using rate-distortion theory, iteratively computes an approximately-value-equivalent, lossy compression of the environment which an agent may feasibly target in lieu of the true model.
The Value of Information When Deciding What to Learn
All sequential decision-making agents explore so as to acquire knowledge about a particular target.
Bad-Policy Density: A Measure of Reinforcement Learning Hardness
We address this question by proposing a simple measure of reinforcement-learning hardness called the bad-policy density.
An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning
How do we formalize the challenge of credit assignment in reinforcement learning?
Deciding What to Learn: A Rate-Distortion Approach
Agents that learn to select optimal actions represent a prominent focus of the sequential decision-making literature.
Randomized Value Functions via Posterior State-Abstraction Sampling
State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms.
Reparameterized Variational Divergence Minimization for Stable Imitation
While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain expert observations, have not been met with the same success.
Flexible and Efficient Long-Range Planning Through Curious Exploration
In contrast, deep reinforcement learning (DRL) methods use flexible neural-network-based function approximators to discover policies that generalize naturally to unseen circumstances.
Deep Reinforcement Learning from Policy-Dependent Human Feedback
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users.
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model.
State Abstractions for Lifelong Reinforcement Learning
We introduce two new classes of abstractions: (1) transitive state abstractions, whose optimal form can be computed efficiently, and (2) PAC state abstractions, which are guaranteed to hold with respect to a distribution of tasks.
A Tale of Two DRAGGNs: A Hybrid Approach for Interpreting Action-Oriented and Goal-Oriented Instructions
Robots operating alongside humans in diverse, stochastic environments must be able to accurately interpret natural language commands.
Modeling Latent Attention Within Neural Networks
Deep neural networks are able to solve tasks across a variety of domains and modalities of data.
Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities
In this work, by grounding commands to all the tasks or subtasks available in a hierarchical planning framework, we arrive at a model capable of interpreting language at multiple levels of specificity ranging from coarse to more granular.
