Skip to content
View songlei00's full-sized avatar
😝
Studying
😝
Studying

Block or report songlei00

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
songlei00/README.md

SongLei 😉

from time import sleep
import school_env_builder
from random import randint


class FoolishStudent:
  
  def __init__(self, agent_name):
    self.agent_name = agent_name
    self.env = school_env_builder.build()
    
  def study(self, epochs):
    for _ in range(epochs):
      state = self.env.reset()
      while True:
        action = randint(0, self.env.action_space.size()-1)
        next_state, reward, done, _ = self.env.step(action)
        if reward < 0:
          print('You are so stupid')
        if done:
          break
        state = next_state
        
  def take_a_break(self, epochs):
    for _ in range(epochs):
      sleep(1)
        
        
if __name__ == '__main__':
  sl = FoolishStudent('songlei')
  for day in range(365):
    sl.study(0)
    sl.take_a_break(10000000000)

Pinned Loading

  1. lamda-bbo/MCTS-VS lamda-bbo/MCTS-VS Public

    Official implementation of NeurIPS'22 paper "Monte Carlo Tree Search based Variable Selection for High-Dimensional Bayesian Optimization"

    Python 30 6

  2. bbo bbo Public

    Black-box optimization for real-world scenario

    Python 2 1

  3. RIBBO RIBBO Public

    Official implementation of "Reinforced In-Context Black-Box Optimization"

    Python 5

  4. easytorch easytorch Public

    基于Python的numpy实现的简易深度学习框架,包括自动求导、优化器、layer等的实现。

    Jupyter Notebook 78 4