haanvid Goto Github PK

agents

TF-Agents is a library for Reinforcement Learning in TensorFlow

alberdice

Office PyTorch implementation of AlberDICE

bcq

PyTorch implementation of BCQ for "Off-Policy Deep Reinforcement Learning without Exploration"

cl1ad

Compositionality Level 1 Action Dataset

cl2ad

Compositionality Level 2 Action Dataset

continuous-policy-learning

deep-reinforcement-learning-papers

A list of recent papers regarding deep reinforcement learning

dice_rl

djl

dstc10-simmc

Repository (preliminary codes) for DSTC10 SIMMC track.

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

google-research

Google Research

gpt-critic

GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems

haanvid.github.io

Personal website

homework

Imitation Learning Homework 1

imitation-dice

kmifqe

Kernel Metric learning for In-sample Fitted Q Evaluation (KMIFQE)

kmis

local kernel metric learning for IS (KMIS) OPE estimation

lspi

LSPI(Least-Squares Policy Iteration) with TF1.5

mc-lave-rl

ICLR 2021: "Monte-Carlo Planning and Learning with Language Action Value Estimates"

models

Models built with TensorFlow

nadaraya-watson-regression-metric

neuralpipeline_dstc8

palr

probability

Probabilistic reasoning and statistical analysis in TensorFlow

repbm

Representation Balancing MDPs for Off-Policy Policy Evaluation

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

rllab-colab-tutorial

sbv

slope-experiments