Search Results for author:
Found 31 papers, 20 papers with code
OpenAI o1 System Card
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.
GPT-4o System Card
We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
Ranked #2 on
Multiple-choice
on Neptune-Full
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
However, evaluating progress on offline RL algorithms requires effective and challenging benchmarks that capture properties of real-world tasks, provide a range of task difficulties, and cover a range of challenges both in terms of the parameters of the domain (e. g., length of the horizon, sparsity of rewards) and the parameters of the data (e. g., narrow demonstration data or broad exploratory data).
Training Diffusion Models with Reinforcement Learning
However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives such as human-perceived image quality or drug effectiveness.
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
In this paper, we reinterpret IQL as an actor-critic method by generalizing the critic objective and connecting it to a behavior-regularized implicit actor.
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment.
FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
We present a system that enables an autonomous small-scale RC car to drive aggressively from visual observations using reinforcement learning (RL).
Efficient Online Reinforcement Learning with Offline Data
Sample efficiency and exploration remain major challenges in online reinforcement learning (RL).
Offline Reinforcement Learning for Visual Navigation
Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved paths, or avoiding freshly mowed grass.
A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
Deep reinforcement learning is a promising approach to learning policies in uncontrolled environments that do not require domain knowledge.
Offline RL for Natural Language Generation with Implicit Language Q Learning
Large language models distill broad knowledge from text corpora.
In Defense of the Unitary Scalarization for Deep Multi-Task Learning
We show that unitary scalarization, coupled with standard regularization and stabilization techniques from single-task learning, matches or improves upon the performance of complex multi-task optimizers in popular supervised and reinforcement learning settings.
RvS: What is Essential for Offline RL via Supervised Learning?
Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL.
Automatic Data Augmentation for Generalization in Reinforcement Learning
Deep reinforcement learning (RL) agents often fail to generalize beyond their training environments.
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
We show that performance of online algorithms for generalization in RL can be hindered in the offline setting due to poor estimation of similarity between observations.
Offline Reinforcement Learning with Implicit Q-Learning
The main insight in our work is that, instead of evaluating unseen actions from the latest policy, we can approximate the policy improvement step implicitly by treating the state value function as a random variable, with randomness determined by the action (while still integrating over the dynamics to avoid excessive optimism), and then taking a state conditional upper expectile of this random variable to estimate the value of the best actions in that state.
Offline Reinforcement Learning with In-sample Q-Learning
The main insight in our work is that, instead of evaluating unseen actions from the latest policy, we can approximate the policy improvement step implicitly by treating the state value function as a random variable, with randomness determined by the action (while still integrating over the dynamics to avoid excessive optimism), and then taking a state conditional upper expectile of this random variable to estimate the value of the best actions in that state.
The Essential Elements of Offline RL via Supervised Learning
These methods, which we collectively refer to as reinforcement learning via supervised learning (RvS), involve a number of design decisions, such as policy architectures and how the conditioning variable is constructed.
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data.
Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation
In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches.
Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
Our agent outperforms other baselines specifically designed to improve generalization in RL.
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training.
Ranked #1 on
Continuous Control
on DeepMind Walker Walk (Images)
Imitation Learning via Off-Policy Distribution Matching
In this work, we show how the original distribution ratio estimation objective may be transformed in a principled manner to yield a completely off-policy objective.
AlgaeDICE: Policy Gradient from Arbitrary Experience
In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility.
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
A promising approach is to learn a latent representation together with the control policy.
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework.
Surface Networks
We study data-driven representations for three-dimensional triangle meshes, which are one of the prevalent objects used to represent 3D geometry.
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
When Bob is deployed on an RL task within the environment, this unsupervised training reduces the number of supervised episodes needed to learn, and in some cases converges to a higher reward.
PlaNet - Photo Geolocation with Convolutional Neural Networks
Is it possible to build a system to determine the location where a photo was taken using just its pixels?
Ranked #1 on
Photo geolocation estimation
on Im2GPS
(Reference images metric)
Depth sweep regression forests for estimating 3d human pose from images
We address the problem of estimating the 3d pose from monocular images.
Ranked #26 on
3D Human Pose Estimation
on HumanEva-I
Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction
In this paper, we propose a novel labeling cost for multi- view reconstruction.
