Tinkoff.AI

CORL

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

etna

ETNA – Time-Series Library

katakomba

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

ReBRAC

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

sac-rnd

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

hifi_vc

palbert

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

eop

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

open-tlab

Примеры пропозалов для подачи заявки в Open.TLab

probabilistic-embeddings

"Probabilistic Embeddings Revisited" paper official repository

lb-sac

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

cnf

Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, Offline RL Workshop

exact

The original PyTorch implementation of the "EXACT: How Train Your Accuracy"

use_rs

pycon-chit-chat

dl-course

sigir-2021

4th place solution for the SIGIR 2021 challenge.

d4rl

A benchmark for offline reinforcement learning.

.github