Public Code

2018-NIPS-RLPO - Learning Internal State Models in Partially Observable Environments

Source code for my submission "Learning Internal State Models in Partially Observable Environments" at the NeurIPS 2018 Workshop on Reinforcement Learning under Partial Observability.

Available at abaisero/2018-nips-rlpo-code.

gym-pomdps - Gym Environments for Flat POMDPs

Implements Gym Environments for arbitrary POMDPs and DecPOMDPs, respectively specified by .POMDP and .DPOMDP files.

Available at abaisero/gym-pomdps.

rl_parsers - Reinforcement Learning Parsers

Stand-alone repository containing parsers for files related to RL. Currently contains parsers for the standard .POMDP and .DPOMDP formats, as well as custom .FSC (Finite State Controller) and .FSS (Finite State Structure) formats which I use for my own research.

Available at abaisero/rl_parsers.

indextools - Tools for Semantic Indexing

Family of classes which represent bijections between sets of $N$ structured and/or semantic values/objects and a corresponding set of indices ${0, \ldots, N-1}$; Useful to represent and access tables of values indexed directly by objects with rich interfaces and attributes.

The provided classes automate (via a user-friendly interface) the conversions between values and indices.

Available at abaisero/indextools.

pytk - Python Toolkit

A personal repository of general purpose utilities including: context managers, decorators, iterators, collections, and 3D geometry classes. This code is in continuous fluctuation, and not significantly stable.

Available at abaisero/pytk.

baise.ro - This Website

This website is developed using Flask, a minimalistic python framework for webapp development which uses the Jinja templating language to build page structure and Markdown to fill in the content. The style is powered by Bootstrap (an HTML/CSS/JS framework) and Font Awesome (an icon toolkit). Despite not being a web developer, these tools allowed me to create this website with ease.

Available at abaisero/baise.ro.