We perform functional grounding of LLMs' knowledge in BabyAI-Text

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.

OPE Tools based on Empirical Study of Off Policy Policy Estimation paper.

Google Research

An index of algorithms for offline reinforcement learning (offline-rl)

PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning

A curated list of awesome model based RL resources (continually updated)

Question Answering with Interactive Text (QAit), code for EMNLP 2019 paper "Interactive Language Learning by Question Answering"

A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems"

Simple and easily configurable grid world environments for reinforcement learning

BabyAI platform. A testbed for training agents to understand and execute language commands.

cordial-sync is a software package than can be used to reproduce the results from the paper "A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks”

RAD: Reinforcement Learning with Augmented Data

Code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning", Ren et al., NeurIPS'20

Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)

Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)

A learning environment for man-made Interactive Fiction games.

Code for Weighted QMIX

The release codes of LA-MCTS with its application to Neural Architecture Search.

Non-parametric Entropy Estimation Toolbox

Estimators for the entropy and other information theoretic quantities of continuous distributions

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

PyTorch implementations of deep reinforcement learning algorithms and environments

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.