Search Results for author:
Found 14 papers, 8 papers with code
Competitive Programming with Large Reasoning Models
We competed live at IOI 2024 with o1-ioi and, using hand-crafted test-time strategies, placed in the 49th percentile.
OpenAI o1 System Card
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.
GPT-4 Technical Report
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
Ranked #1 on
Question Answering
on PeerQA
Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters.
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization ($\mu$P), many optimal HPs remain stable even as model size changes.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
Learning Dexterous In-Hand Manipulation
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand.
Emergent Complexity via Multi-Agent Competition
In this paper, we point out that a competitive multi-agent environment trained with self-play can produce behaviors that are far more complex than the environment itself.
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks.
Parameter Space Noise for Exploration
Combining parameter noise with traditional RL methods allows to combine the best of both worlds.
UCB Exploration via Q-Ensembles
We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning.
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients.
Ranked #1 on
Atari Games
on Atari 2600 Pong
Occam's Gates
We present a complimentary objective for training recurrent neural networks (RNN) with gating units that helps with regularization and interpretability of the trained model.
