Peter Henderson's repositories
RLSSContinuousControlTutorial
Tutorial on continuous control at Reinforcement Learning Summer School 2017.
MultiStepBootstrappingInRL
Here, we compare Q(\sigma) learning presented by Sutton and Barto in [1] to Tree-Backup, n-step Expected Sarsa, and n-step Sarsa.
SarsaVsExpectedSarsa
An a bias-variance tradeoff of Sarsa vs. Expected Sarsa with experiments.
ValuePolicyIterationVariations
Experiments testing variants of Value and Policy iterations.
TemporalYolo
Experiments on temporal YOLO
Option-Critic-Turing-Machines
A development toybox and pitch for integrating the option-critic architecture with neural turing machines.
TemporalDeepQLearning
Experiments in temporal deep Q learning
BrachialNerveSegmentation
Experiments for Kaggle competition (got top 10% with one of the models): https://www.kaggle.com/c/ultrasound-nerve-segmentation
DialogueSystemPresentation
Presentation for COMP-599 on a dialogue response task
DrQA
A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.
EndToEndPresentation
Presentation for reading group on Levine et al. End-to-end Learning of Visuomotor Policies
hate-speech-and-offensive-language
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Imitation_Learning_RL
Imitation Learning in Deep RL
modular_rl
Implementation of TRPO and related algorithms
parallel-trpo
A parallel version of Trust Region Policy Optimization
pytorch-trpo
PyTorch implementation of Trust Region Policy Optimization
rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
SpotIt
See the Spotted events happening near you
yolo_tensorflow
Tensorflow implementation of YOLO, including training and test phase.
Zennectome
A library for analysis of connectomes. Provides CLI's for community detection, unifying several external libraries to make analysis easy.