515 citations · 1.1k across the 16 of their papers we have counts for
17 papers
Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13
Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…
Deploying Offline Reinforcement Learning with Human Feedback
Ziniu Li, Ke Xu, Liu Liu +3
Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an of…
Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance
Kelvin Xu, Zheyuan Hu, Ria Doshi +4
Complex and contact-rich robotic manipulation tasks, particularly those that involve multi-fingered hands and underactuated object manipulation, present a significant challenge to…
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
Chengqian Gao, Ke Xu, Liu Liu +3
A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. Howev…
Autonomous Reinforcement Learning: Formalism and Benchmarking
Archit Sharma, Kelvin Xu, Nikhil Sardana +4
Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of…
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention
Abhishek Gupta, Justin Yu, Tony Z. Zhao +5
Reinforcement Learning (RL) algorithms can in principle acquire complex robotic skills by learning from large amounts of data in the real world, collected via trial and error. Howe…
Continual Learning of Control Primitives: Skill Discovery via Reset-Games
Kelvin Xu, Siddharth Verma, Chelsea Finn +1
Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challen…
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin +8
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and d…
Probabilistic Model-Agnostic Meta-Learning
Chelsea Finn, Kelvin Xu, Sergey Levine
Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical ch…
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
Kelvin Xu, Ellis Ratner, Anca Dragan +2
A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. In…
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Ofir Nachum, Mohammad Norouzi, Kelvin Xu +1
Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective f…
Bridging the Gap Between Value and Policy Based Reinforcement Learning
Ofir Nachum, Mohammad Norouzi, Kelvin Xu +1
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality un…
Unsupervised Perceptual Rewards for Imitation Learning
Pierre Sermanet, Kelvin Xu, Sergey Levine
Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks,…
An Actor-Critic Algorithm for Sequence Prediction
Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu +5
We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are li…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
A Controller-Recognizer Framework: How necessary is recognition for control?
Marcin Moczulski, Kelvin Xu, Aaron Courville +1
Recently there has been growing interest in building active visual object recognizers, as opposed to the usual passive recognizers which classifies a given static image into a pred…
On Using Monolingual Corpora in Neural Machine Translation
Caglar Gulcehre, Orhan Firat, Kelvin Xu +6
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation. Arguably, one of the major factors…