Motivations and Goals |
---|
Become familiar with t4a-rl assignment |
Install and become familiar with t4a-rl setup |
Design a simple reward function and a dummy absorbing state definition |
Tasks (teacher) |
T4a-rl (5 Points) Reinforcement Learning |
python3 --version
sudo apt update sudo sudo add-apt-repository ppa:deadsnakes/ppa -y sudo apt install python3.10-full -y
sudo apt install python3-pip -y pip3 install virtualenv --upgrade virtualenv inchworm_rl_venv --python=python3.10
source inchworm_rl_venv/bin/activate && pip3 install -r requirements.txt
The previously mentioned steps are summarized in the provided install-venv.sh
.
To familiarize yourself with the simulator setup, it is recommended that you use the MuJoCo simulator outside the reinforcement learning pipeline by following these steps.
bin/simulate.sh
in the MuJoCo unpacked archive root directory).
inchworm.xml
from the model
directory by dragging and dropping it into the MuJoCo window.
Then you are free to
4
key,
1
key.
Note that visual elements are purely visual and play no role during training.
Examine the robot part names under Rendering tab in the left column.
is_touching
,
Design a simple reward function that uses the average forward speed of the first and last servomotors in centimetres per second.
Design a simple absorbing state detection such that any state that touches the ground with other parts than scales and bumpers results in marking it as absorbing.
Extend by previously implemented simple reward function by penalizing states where joint-1
and joint-2
move significantly close to the ground, i.e. below 0 degrees.