yardenas Goto Github PK

asyarden.com

Just my very simple personal website

awesome-llm-human-preference-datasets

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

budget-tracking

A 'Dash'-based dashboard for my budget

cartographer

Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.

cliff-daredevil

A simple 2D car driving environment for safe decision making

dreamer

Dream to Control: Learning Behaviors by Latent Imagination

ethz-advanced-ml

ethz-safe-learning

Safe Model-Based Reinforcement Learning via Ensembles and Model Predictive Control

ethz-vision-algorithms

Python implementation of various vision algorithms as part of "Vision Algorithms for Mobile Robotics" course

jax-dreamer

Dreamer on JAX

jax-pacoh-nn

jax-sac

Implementation of Soft Actor-Critic in JAX

kneed-walker

la-mbda

LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization

lbsgd-rl

Implementation of Log Barriers SGD used in the RL experiment of the "Log Barriers for Safe Optimization of Smooth Objectives and Constraints with Application to Reinforcement Learning" paper.

meta-learning-tutorial

Implementation of MAML with JAX. Playing a bit with Omniglot and Sinusoidal toy problems.

nanotron

Minimalistic large language model 3D-parallelism training

nvim-journey

Config file for nvim

offline-meta-mbrl

pacoh-smbrl

pcl-pose-estimation

probabilistic-regression

A short tutorial on Bayesian Neural Networks with JAX

rolling-disk

safe-adaptation-agents

Implementation of adaptive constrained RL algorithms. Child repository of @lasgroup/safe-adaptation-gym

safe-adaptation-gym

A Safety-Gym based benchmark suite for safe meta RL

safe-adaptation-starter-agents

Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.

safe-control-as-inference

safety-gym

talks

My Slidev slides

the-lazy-experimentalist

Helping myself run more (remote) experiments with less (fingers) effort