Breakend/SarsaVsExpectedSarsa Breakend/SarsaVsExpectedSarsa

  • Stars
    star
    8
  • Rank 2,099,232 (Top 42 %)
  • Language
    Jupyter Notebook
  • Created almost 8 years ago
  • Updated almost 8 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
Breakend/SarsaVsExpectedSarsa
github

Breakend

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

An a bias-variance tradeoff of Sarsa vs. Expected Sarsa with experiments.

More Repositories

1

experiment-impact-tracker

Python
266
star
2

gym-extensions

This repo is intended as an extension for OpenAI Gym for auxiliary tasks (multitask learning, transfer learning, inverse reinforcement learning, etc.)
Python
213
star
3

DeepReinforcementLearningThatMatters

Accompanying code for "Deep Reinforcement Learning that Matters"
Python
153
star
4

PileOfLaw

A dataset for pretraining language models targeted for legal tasks.
Jupyter Notebook
113
star
5

DialogDatasets

A repository linking to publicly available dialog datasets. Feel free to send pull requests.
HTML
66
star
6

MotionDetection

A project on motion detection in a noisy environment (shaky or moving camera), through background subtraction with single Gaussian models.
C++
47
star
7

OptionGAN

Code accompanying the OptionGAN paper.
Python
43
star
8

echo

Android Mesh Networking Chat with WiFI-Direct
Java
36
star
9

RLSSContinuousControlTutorial

Tutorial on continuous control at Reinforcement Learning Summer School 2017.
Python
34
star
10

ReproducibilityInContinuousPolicyGradientMethods

These are experiments for examining reproducibility in Policy Gradient RL algorithms in Continuous domains. Mainly using the Rllab implementation.
Python
18
star
11

EthicsInDialogue

OpenEdge ABL
15
star
12

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.
Python
14
star
13

SocraticSwarm

A simulator and algorithms using deccentralized receding horizon control for coordinating autonomous UAV systems in completing a search task.
C#
14
star
14

SelfDestructingModels

Python
12
star
15

BayesianPolicyGradients

Python
7
star
16

CMACvTileCode

Python
7
star
17

ValuePolicyIterationVariations

Experiments testing variants of Value and Policy iterations.
Jupyter Notebook
5
star
18

ExperimentsInIRL

Python
4
star
19

TemporalYolo

Experiments on temporal YOLO
Python
4
star
20

WhatShouldICite

This is an informal record of original citations that I'm aware of for key terms in scientific literature. It started because I didn't know what's the original work to cite for eligibility traces and it seems important to do proper credit assignment.
4
star
21

orion-pytorch-ppo-acktr-a2c

An adapted version of the ikostrikov RL algorithm implementation for use with the Orรญon hyperparameter optimization framework.
Python
3
star
22

DeepMultiObjectTracking

Python
2
star
23

ClimateChangeFromMachineLearningResearch

Python
2
star
24

drqawrapper

Python
2
star
25

AdversarialGain

Python
2
star
26

echo-laptop

This is the laptop client to to connect to echo nodes
Java
1
star
27

LLM-Tuning-Safety.github.io

CSS
1
star
28

TARProtocols

Dataset of Discovery Validation Protocols
HTML
1
star
29

NeurIPS

A mirror for some of the NeurIPS website content with a new acronym.
HTML
1
star
30

Option-Critic-Turing-Machines

A development toybox and pitch for integrating the option-critic architecture with neural turing machines.
Jupyter Notebook
1
star
31

RL-Energy-Leaderboard

Python
1
star
32

AquaBoxDataset

A dataset for bounding box prediction in underwater environments of the Aqua-family of hexapod robots.
1
star
33

Vulnerabilities-In-Discovery-Tech-Experiment-1

Python
1
star
34

NLPAssignment1

Code for Comp599 Assignment 1 (TAC document classification using simple algos and uni/bigram models)
Python
1
star
35

TemporalDeepQLearning

Experiments in temporal deep Q learning
Python
1
star