mantle2048

rlplot

rlplot is an easy to use and highly encapsulated RL plot library (including basic error bar lineplot and a wrapper to "rliable").

leetcode-Weekly-competition-

力扣周赛

reRLs

A collection of RL papers reproduced by mantle 2048

soccer-ai-imitation

Imitate specific soccer ai goal style

drq_jax

Jax Implementation of Data-regularized Q (DrQ)

.dotfiles

_mantle dotfiles for linux

CS285-2020Fall-Homework

CS285-2020Fall homework implemented by PyTorch

mantle-window-terminal

mantle-window-terminal-settings

reDiffusions

Diffusion algorithms implemented by mantle2048

reLLMs

An unofficial rerun of foundation models (llama, gpt) on benchmarks

Awesome-Story-Generation

This project collects awesome papers on story generation, with a focus on the LLM era papers.

BooookScore

chain-of-thought-hub

:-)

Course-Setting-of-Compiling-Principle

DUT__mantle

creativity_eval

cs182_sp22_hw

cs182_sp22_hw

diverse_openloop

DLkit

mainstream deep learning algorithms implemented by mantle2048

go-fdu-network

login the inside network of fdu

gym_custom_terrain

custom gym env

mantle-missing-semester

Exercise_for_https://missing-semester-cn.github.io/

mantle2048.github.io

My personal academic page

my_assets

ppo_super_mario

reILs

A collection of IL papers reproduced by mantle 2048

rl_theory_slides

rl theory slides from ieor8100: https://ieor8100.github.io/rl/

textbook_quality

Generate textbook-quality LLM pretraining data

torchtune

A Native-PyTorch Library for LLM Fine-tuning

working-time-download

公司工作作息表

WorkingTime