In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss

2 code implementations • 16 Feb 2024 • Yuri Kuratov, Aydar Bulatov, Petr Anokhin, Dmitry Sorokin, Artyom Sorokin, Mikhail Burtsev

This paper addresses the challenge of processing long documents using generative transformer models.

TreeDQN: Learning to minimize Branch-and-Bound tree

1 code implementation • 9 Jun 2023 • Dmitry Sorokin, Alexander Kostin

Combinatorial optimization problems require an exhaustive search to find the optimal solution.

Combinatorial Optimization reinforcement-learning +1

Insights From the NeurIPS 2021 NetHack Challenge

1 code implementation • 22 Mar 2022 • Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, DaeJin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich Küttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim Rocktäschel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, Michał Sypetkowski

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge.

NetHack Reinforcement Learning (RL)

Aligning an optical interferometer with beam divergence control and continuous action space

1 code implementation • 9 Jul 2021 • Stepan Makarenko, Dmitry Sorokin, Alexander Ulanov, A. I. Lvovsky

Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups.

reinforcement-learning Reinforcement Learning (RL)

Adaptation of Quadruped Robot Locomotion with Meta-Learning

no code implementations • 8 Jul 2021 • Arsen Kuzhamuratov, Dmitry Sorokin, Alexander Ulanov, A. I. Lvovsky

Animals have remarkable abilities to adapt locomotion to different terrains and tasks.

Meta-Learning Meta Reinforcement Learning +2

Interferobot: aligning an optical interferometer by a reinforcement learning agent

1 code implementation • NeurIPS 2020 • Dmitry Sorokin, Alexander Ulanov, Ekaterina Sazhina, Alexander Lvovsky

Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots.

reinforcement-learning Reinforcement Learning (RL)

Local Bayesian Optimization of Motor Skills

no code implementations • ICML 2017 • Riad Akrour, Dmitry Sorokin, Jan Peters, Gerhard Neumann

Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization.

Bayesian Optimization Imitation Learning