Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

1 code implementation • 5 Feb 2024 • Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad H. Danesh, Cyril Roumégous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João G. M. Araújo, Guorui Quan, Daniel Tan, Timo Klein, Rujikorn Charakorn, Mark Towers, Yann Berthelot, Kinal Mehta, Dipam Chakraborty, Arjun KG, Valentin Charraut, Chang Ye, Zichen Liu, Lucas N. Alegre, Alexander Nikulin, Xiao Hu, Tianlin Liu, Jongwook Choi, Brent Yi

As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone.

reinforcement-learning Reinforcement Learning (RL)

In-Context Reinforcement Learning for Variable Action Spaces

1 code implementation • 20 Dec 2023 • Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov

Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context.

Multi-Armed Bandits reinforcement-learning

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

1 code implementation • 19 Dec 2023 • Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov

Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research.

Meta-Learning Meta Reinforcement Learning +1

Emergence of In-Context Reinforcement Learning from Noise Distillation

1 code implementation • 19 Dec 2023 • Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks.

reinforcement-learning

Katakomba: Tools and Benchmarks for Data-Driven NetHack

1 code implementation • NeurIPS 2023 • Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov

NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions.

D4RL NetHack +2

Revisiting the Minimalist Approach to Offline Reinforcement Learning

1 code implementation • NeurIPS 2023 • Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin, Sergey Kolesnikov

Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity.

D4RL Offline RL +2

Anti-Exploration by Random Network Distillation

3 code implementations • 31 Jan 2023 • Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov

Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-distribution actions in offline reinforcement learning.

D4RL

Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size

2 code implementations • 20 Nov 2022 • Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Dmitry Akimov, Sergey Kolesnikov

Training large neural networks is known to be time-consuming, with the learning duration taking days or even weeks.

Offline RL

Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

2 code implementations • 20 Nov 2022 • Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov

This Normalizing Flows action encoder is pre-trained in a supervised manner on the offline dataset, and then an additional policy model - controller in the latent space - is trained via reinforcement learning.

Offline RL reinforcement-learning +1

CORL: Research-oriented Deep Offline Reinforcement Learning Library

3 code implementations • NeurIPS 2023 • Denis Tarasov, Alexander Nikulin, Dmitry Akimov, Vladislav Kurenkov, Sergey Kolesnikov

CORL is an open-source library that provides thoroughly benchmarked single-file implementations of both deep offline and offline-to-online reinforcement learning algorithms.

Benchmarking D4RL +1

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

no code implementations • 17 Feb 2022 • Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, François Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman

With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.