Search Results - "Yarats, Denis"

Learning Navigation Skills for Legged Robots with Learned Robot Embeddings by Truong, Joanne, Yarats, Denis, Li, Tianyu, Meier, Franziska, Chernova, Sonia, Batra, Dhruv, Rai, Akshara

“…Recent work has shown results on learning navigation policies for idealized cylinder agents in simulation and transferring them to real wheeled robots…”
Get full text

On the adequacy of untuned warmup for adaptive optimization by Ma, Jerry, Yarats, Denis

“…Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for…”
Get full text

The Differentiable Cross-Entropy Method by Amos, Brandon, Yarats, Denis

“…We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable…”
Get full text

Quasi-hyperbolic momentum and Adam for deep learning by Ma, Jerry, Yarats, Denis

“…Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as…”
Get full text

Hierarchical Text Generation and Planning for Strategic Dialogue by Yarats, Denis, Lewis, Mike

“…End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We…”
Get full text

Watch and Match: Supercharging Imitation with Regularized Optimal Transport by Haldar, Siddhant, Mathur, Vaibhav, Yarats, Denis, Pinto, Lerrel

“…Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often…”
Get full text

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels by Kostrikov, Ilya, Yarats, Denis, Fergus, Rob

“…We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly…”
Get full text

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning by Yarats, Denis, Fergus, Rob, Lazaric, Alessandro, Pinto, Lerrel

“…We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach…”
Get full text

Reinforcement Learning with Prototypical Representations by Yarats, Denis, Fergus, Rob, Lazaric, Alessandro, Pinto, Lerrel

“…ICML 2021 Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL,…”
Get full text

On the model-based stochastic value gradient for continuous reinforcement learning by Amos, Brandon, Stanton, Samuel, Yarats, Denis, Wilson, Andrew Gordon

“…For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of…”
Get full text

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning by Raileanu, Roberta, Goldstein, Max, Yarats, Denis, Kostrikov, Ilya, Fergus, Rob

“…Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar…”
Get full text

CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery by Laskin, Michael, Liu, Hao, Peng, Xue Bin, Yarats, Denis, Rajeswaran, Aravind, Abbeel, Pieter

“…We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions…”
Get full text

Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning by Yarats, Denis, Brandfonbrener, David, Liu, Hao, Laskin, Michael, Abbeel, Pieter, Lazaric, Alessandro, Pinto, Lerrel

“…Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement…”
Get full text

Hierarchical Decision Making by Generating and Following Natural Language Instructions by Hu, Hengyuan, Yarats, Denis, Gong, Qucheng, Tian, Yuandong, Lewis, Mike

“…We explore using latent natural language instructions as an expressive and compositional representation of complex actions for hierarchical decision making…”
Get full text

URLB: Unsupervised Reinforcement Learning Benchmark by Laskin, Michael, Yarats, Denis, Liu, Hao, Lee, Kimin, Zhan, Albert, Lu, Kevin, Cang, Catherine, Pinto, Lerrel, Abbeel, Pieter

“…Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks. Yet training generalist agents that…”
Get full text

Learning Navigation Skills for Legged Robots with Learned Robot Embeddings by Truong, Joanne, Yarats, Denis, Li, Tianyu, Meier, Franziska, Chernova, Sonia, Batra, Dhruv, Rai, Akshara

“…Recent work has shown results on learning navigation policies for idealized cylinder agents in simulation and transferring them to real wheeled robots…”
Get full text

Improving Sample Efficiency in Model-Free Reinforcement Learning from Images by Yarats, Denis, Zhang, Amy, Kostrikov, Ilya, Amos, Brandon, Pineau, Joelle, Fergus, Rob

“…Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising…”
Get full text

Generalized Inner Loop Meta-Learning by Grefenstette, Edward, Amos, Brandon, Yarats, Denis, Htut, Phu Mon, Molchanov, Artem, Meier, Franziska, Kiela, Douwe, Cho, Kyunghyun, Chintala, Soumith

“…Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution…”
Get full text

Deal or No Deal? End-to-End Learning for Negotiation Dialogues by Lewis, Mike, Yarats, Denis, Dauphin, Yann N, Parikh, Devi, Batra, Dhruv

“…Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. Negotiations require…”
Get full text

Convolutional Sequence to Sequence Learning by Gehring, Jonas, Auli, Michael, Grangier, David, Yarats, Denis, Dauphin, Yann N

“…The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce…”
Get full text