abagaria

skill-chaining

Implementation of "Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining"

hrl

Robust deep skill chaining

transformer

language model using transformer architecture

abagaria.github.io

Build a beautiful and simple website in literally minutes. Demo at http://deanattali.com/beautiful-jekyll

parse-reranker-1

seq2seq

Implementation of "Neural Machine Translation of Rare Words with Subword Units" by Sennrich et al.

simple_rl

A simple framework for experimenting with Reinforcement Learning in Python.

affordances

Learning option initiation set classifier

annotated-transformer

http://nlp.seas.harvard.edu/2018/04/03/attention.html

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

contingency

Implementation of Contingency-Aware Exploration in Reinforcement Learning

deep-svdd

DeepRL

Modularized Implementation of Deep RL Algorithms in PyTorch

dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

dreamerv2

Mastering Atari with Discrete World Models

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Hierarchical-Actor-Critc-HAC-

This repository contains the code to implement the Hierarchical Actor-Critic (HAC) algorithm.

lwm

Latent World Models For Intrinsically Motivated Exploration | Official repository

markov-state-abstractions

Image-based gridworld experiment for learning Markov state abstractions

Master-Template

Template and style files for ICLR

neural-sentiment-classification

Assignment for computational semantics course

opiq

Code for Optimistic Exploration even with a Pessimistic Initialisation

quantile

Playing around with regression problems

Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

RBFDQN

rlpyt

Reinforcement Learning in PyTorch

sentiment-classification

treelstm.pytorch

Tree LSTM implementation in PyTorch

visgrid

RL environments for quickly running image-based grid-world experiments

visual-grounding