Tinkoff.AI

ETNA – Time-Series Library

tinkoff-ai

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

tinkoff-ai

Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022

tinkoff-ai

Code for the paper "PALBERT: Teaching ALBERT to Ponder", NeurIPS 2022 Spotlight

tinkoff-ai

Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023

tinkoff-ai

Official implementation for "Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size", NeurIPS 2022, Offline RL Workshop

tinkoff-ai

Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

tinkoff-ai

tinkoff-ai

Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)

tinkoff-ai

Примеры пропозалов для подачи заявки в Open.TLab

tinkoff-ai