davidslayback Goto Github PK

autoinit

AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks

beamerthemenu

Beamer theme for Northeastern University

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features

coagent-networks-revisited

davidslayback

docs

The open-source repo for docs.github.com

dts-dbg-gh-act

Testing github actions workflows in safety

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-po-taxi

Partially-observable taxi environment, with internal vectorization

gym-pomdps

gymnasium

A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)

gymnax

RL Environments in JAX 🌍

jax-toolkit

Commonly used JAX functions, mostly focused around dm-haiku

mc_power_med

Shiny app for Monte Carlo Power analysis for Mediation Models

megaverse

High-throughput simulation platform for Artificial Intelligence reseach

online-pomdp-planning-experiments

Experiments for (MCTS) planning in POMDPs with options

po-brax

Partially-observable and/or hierarchical tasks in brax

pomdp-domains

A collection of pomdp domains in robotics.

pwr2ppl

pwr2ppl: Power analyses for a wide range common behavioral science research designs

rlpyt

Reinforcement Learning in PyTorch

torch-toolkit

Set of commonly-used functions and tools for PyTorch reinforcement learning