| # train_grpo.py | |
| import re | |
| import torch | |
| from datasets import load_dataset, Dataset | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| from peft import LoraConfig | |
| from trl import GRPOConfig, GRPOTrainer | |
| # Load and prep dataset |
| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
| import numpy as np | |
| import cPickle as pickle | |
| import gym | |
| # hyperparameters | |
| H = 200 # number of hidden layer neurons | |
| batch_size = 10 # every how many episodes to do a param update? | |
| learning_rate = 1e-4 | |
| gamma = 0.99 # discount factor for reward |
The goal here is to build mxnet.io on Windows. This was tested on Windows 10. Overall, the procedure is to compile mxnet to generate an up-to-date libmxnet.dll. Once we have that, we will build and install the R package containing all dependent libraries, including the newly-built libmxnet.dll.
This guide was adapted from the primary setup documentation http://mxnet.io/get_started/setup.html which seems out-of-date.