research
∙
06/02/2023
Probabilistic Adaptation of Text-to-Video Models
Large text-to-video models trained on internet-scale data have demonstra...
share
research
∙
03/07/2023
Gradient-Free Structured Pruning with Unlabeled Data
Large Language Models (LLMs) have achieved great success in solving diff...
research
∙
03/07/2023
Foundation Models for Decision Making: Problems, Methods, and Opportunities
Foundation models pretrained on diverse data at scale have demonstrated ...
research
∙
01/31/2023
Learning Universal Policies via Text-Guided Video Generation
A goal of artificial intelligence is to construct an agent that can solv...
research
∙
01/16/2023
The Role of Baselines in Policy Gradient Optimization
We study the effect of baselines in on-policy stochastic policy gradient...
research
∙
01/10/2023
Memory Augmented Large Language Models are Computationally Universal
We show that transformer-based large language models are computationally...
research
∙
12/17/2022
Latent Variable Representation for Reinforcement Learning
Deep latent variable models have achieved significant empirical successe...
research
∙
11/30/2022
Score-based Continuous-time Discrete Diffusion Models
Score-based modeling through stochastic differential equations (SDEs) ha...
research
∙
11/28/2022
What learning algorithm is in-context learning? Investigations with linear models
Neural sequence models, especially transformers, exhibit a remarkable ca...
research
∙
11/21/2022
TEMPERA: Test-Time Prompting via Reinforcement Learning
Careful prompt design is critical to the use of large language models in...
research
∙
11/14/2022
Learning to Optimize with Stochastic Dominance Constraints
In real-world decision-making, uncertainty is important yet difficult to...
research
∙
10/24/2022
Dichotomy of Control: Separating What You Can Control from What You Cannot
Future- or return-conditioned supervised learning is an emerging paradig...
research
∙
09/16/2022
Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
Optimal scaling has been well studied for Metropolis-Hastings (M-H) algo...
research
∙
08/19/2022
Spectral Decomposition Representation for Reinforcement Learning
Representation learning often plays a critical role in reinforcement lea...
research
∙
07/14/2022
Making Linear MDPs Practical via Contrastive Representation Learning
It is common to address the curse of dimensionality in Markov decision p...
research
∙
07/02/2022
Rationale-Augmented Ensembles in Language Models
Recent research has shown that rationales, or step-by-step chains of tho...
research
∙
06/29/2022
Discrete Langevin Sampler via Wasserstein Gradient Flow
Recently, a family of locally balanced (LB) samplers has demonstrated ex...
research
∙
05/27/2022
Multimodal Masked Autoencoders Learn Transferable Representations
Building scalable models to learn from diverse, multimodal data remains ...
research
∙
05/22/2022
Chain of Thought Imitation with Procedure Cloning
Imitation learning aims to extract high-performance policies from logged...
research
∙
05/21/2022
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
We propose a novel prompting strategy, least-to-most prompting, that ena...
research
∙
04/25/2022
Reinforcement Teaching
We propose Reinforcement Teaching: a framework for meta-learning in whic...
research
∙
03/21/2022
Self-Consistency Improves Chain of Thought Reasoning in Language Models
We explore a simple ensemble strategy, self-consistency, that significan...
research
∙
02/02/2022
On the Effect of Log-Barrier Regularization in Decentralized Softmax Gradient Play in Multiagent Systems
Softmax policy gradient is a popular algorithm for policy optimization i...
research
∙
01/28/2022
Chain of Thought Prompting Elicits Reasoning in Large Language Models
Although scaling up language model size has reliably improved performanc...
research
∙
12/01/2021
Neural Stochastic Dual Dynamic Programming
Stochastic dual dynamic programming (SDDP) is a state-of-the-art method ...
research
∙
10/29/2021
Understanding the Effect of Stochasticity in Policy Optimization
We study the effect of stochasticity in on-policy policy optimization, a...
research
∙
10/28/2021
SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
Knowledge graphs (KGs) capture knowledge in the form of head–relation–ta...
research
∙
07/12/2021
Combiner: Full Attention Transformer with Sparse Computation Cost
Transformers provide a class of expressive architectures that are extrem...
research
∙
06/18/2021
On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data
We study the fundamental question of the sample complexity of learning a...
research
∙
06/13/2021
Characterizing the Gap Between Actor-Critic and Policy Gradient
Actor-critic (AC) methods are ubiquitous in reinforcement learning. Alth...
research
∙
05/13/2021
Leveraging Non-uniformity in First-order Non-convex Optimization
Classical global convergence results for first-order methods rely on uni...
research
∙
04/15/2021
Joint Attention for Multi-Agent Coordination and Social Learning
Joint attention - the ability to purposefully coordinate attention with ...
research
∙
04/06/2021
On the Optimality of Batch Policy Optimization Algorithms
Batch policy optimization considers leveraging existing data for policy ...
research
∙
02/11/2021
Optimization Issues in KL-Constrained Approximate Policy Iteration
Many reinforcement learning algorithms can be seen as versions of approx...
research
∙
12/12/2020
Offline Policy Selection under Uncertainty
The presence of uncertainty in policy evaluation significantly complicat...
research
∙
11/10/2020
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Discrete structures play an important role in applications like program ...
research
∙
10/22/2020
CoinDICE: Off-Policy Confidence Interval Estimation
We study high-confidence behavior-agnostic off-policy evaluation in rein...
research
∙
09/29/2020
Attention that does not Explain Away
Models based on the Transformer architecture have achieved better accura...
research
∙
07/21/2020
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
Off-policy reinforcement learning (RL) holds the promise of sample-effic...
research
∙
07/07/2020
Off-Policy Evaluation via the Regularized Lagrangian
The recently proposed distribution correction estimation (DICE) family o...
research
∙
06/28/2020
Scalable Deep Generative Modeling for Sparse Graphs
Learning graph generative models is a challenging task for deep learning...
research
∙
06/17/2020
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
This work focuses on off-policy evaluation (OPE) with function approxima...
research
∙
05/13/2020
On the Global Convergence Rates of Softmax Policy Gradient Methods
We make three contributions toward better understanding policy gradient ...
research
∙
03/17/2020
Energy-Based Processes for Exchangeable Data
Recently there has been growing interest in modeling sets with exchangea...
research
∙
03/09/2020
Variational Inference for Deep Probabilistic Canonical Correlation Analysis
In this paper, we propose a deep probabilistic multi-view model that is ...
research
∙
03/02/2020
Batch Stationary Distribution Estimation
We consider the problem of approximating the stationary distribution of ...
research
∙
02/27/2020
ConQUR: Mitigating Delusional Bias in Deep Q-learning
Delusional bias is a fundamental source of error in approximate Q-learni...
research
∙
02/21/2020
GenDICE: Generalized Offline Estimation of Stationary Values
An important problem that arises in reinforcement learning and Monte Car...
research
∙
12/24/2019
Learning to Combat Compounding-Error in Model-Based Reinforcement Learning
Despite its potential to improve sample complexity versus model-free app...
research
∙
12/04/2019