Reinforcement Learning in 3 Hours | Full Course using Python
Why Stack Overflow recommends it
Stack Overflow users link it as the tutorial they are following when they hit errors with Stable Baselines, Gym and Atari ROM setup.
Recommended by 0 people across 0 different months, 2021 to 2023.
What it is
A three-hour beginner course by Nicholas Renotte on reinforcement learning with Python, OpenAI Gym and Stable Baselines 3. It covers setup, environments, training, evaluation, TensorBoard logging, and building custom environments, with agents for CartPole, Breakout and CarRacing.
What people said
Cites Cole · 2021-10 · Stack Overflow · on “How do I install the Atari environments from openai-gym?”
In this video ( [this video] ) at the 1:47:40 mark, he types in the following code: !python -m atari_py.import_roms .\ROMS\ROMS I have already downloaded the ROMS folder and the path for it is 'current_directory/ROMS/ROMS' so I believe the last part of this command is correct. However, when I run this command I get the following error: Traceback (most recent call last): File "C:\Users\my_username\anaconda3\lib\runpy.py", line 185, in _run_module_as_main mod_name, mod_spec, code = _get_module_details(mod_name, _Error) File "C:\Users\my_username\anaconda3\lib\runpy.py", line 111, in _get_module_details __import__(pkg_name) File "C:\Users\my_username\anaconda3\lib\site-packages\atari_py\__init__.py"
Cites Rytro · 2022-12 · Stack Overflow · on “Exception has occurred: ValueError too many values to unpack (expected 2)line 13”
im getting an error saying: Exception has occurred: ValueError too many values to unpack (expected 2) File "D:\Game Developlment\AI\Learning\Pong ai NEAT\mainTutorial.py", line 13, in <module> model.learn(total_timesteps=20000) im trying to follow a (this tutorial) [this video] which is about Reinforcement learning in python. im 59:17 in to the video(if that matters) and i really want to be able to train my own AI. Does anyone know a fix? I dont get any errors in the terminal, but it doesnt do anything Code: import os import gym from stable_baselines3 import PPO from stable_baselines3.common.vec_env import DummyVecEnv from stable_baselines3.common.evaluation import evaluate_policy Environment_nam
Cites user3533030 · 2023-02 · Stack Overflow · on “StableBaselines3 / steps vs. total_timesteps vs. number of times environment is solved during training”
model.learn(total_timesteps=20) takes much longer than I expected, so I'm trying to understand if I should: Be frugal with time steps Speed up my environment env.step(action) Train even more time steps Consider a simple environment: There are (x3) steps until done=True I expected model.learn(total_timesteps=20) to take either: 20 x 3 steps = 20 iterations (equiv. to 20 episodes) 20 total steps (or perhaps 18 or 21 steps) = (x6) or (x7) episodes This is a similar question and has no answer: Stackoverflow question A [LINK] . This answer ( Stackoverflow question B [LINK] ) implies that this is truly the total number of steps for all iterations of the env . If this is the case, in my example abo