Asap7772

PTR

This repository contains the implementation of the PTR algorithm described in the paper: Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning.

understanding-rlhf

DeepCriminalize

Project that uses GAN's to develop a sketch artist like representation of a criminal. Winners of the Cal Hack Fellowship 2019

widowx_control

antmaze_gen

byol_rl

D4RL

A collection of reference environments for offline reinforcement learning

epickitchensproc

gridworld_notebook

Cal-QL

PeerWalk

PeerWalk is a React-Native app to allow verified college students to schedule walks with peers to safely walk around campus. Created at the Facebook San Francisco Hackathon (FBSF).

Asap7772.github.io

Resume Website

asr_lab

EE 225D ASR Lab

bet

Code and website for Behavior Transformers: Cloning k modes with one stone.

cog

dpo

genpaths

inac_baseline

JaxCQL

Conservative Q learning in Jax

jaxrl2_finetuning_benchmark

kitchen_eval

pythia

ReDS

rt1_eval

scripts_tpus

spring2024-assignment1-basics

TrajWeightingBaseline

trl

Train transformer language models with reinforcement learning.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

website