\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"```{important}\n",
"- We strongly recommend using **Google Chrome web browser** for the video.\n",
"- The video can only be viewed on a Google account registered for the **premium course**.\n",
" - Can't see the video even though you're registered for the premium course? \n",
" - Troubleshooting Video Playback Issues\n",
"- **Add Q&A comments**: You can write a question comment on the video by clicking the `Pop out` button in the top right corner of the video.\n",
"```"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Resources"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 1\n",
"- Time trial - follow the center line\n",
"```python3\n",
"def reward_function(params):\n",
" '''\n",
" Example of rewarding the agent to follow center line\n",
" '''\n",
" \n",
" # Read input parameters\n",
" track_width = params['track_width']\n",
" distance_from_center = params['distance_from_center']\n",
" \n",
" # Calculate 3 markers that are at varying distances away from the center line\n",
" marker_1 = 0.1 * track_width\n",
" marker_2 = 0.25 * track_width\n",
" marker_3 = 0.5 * track_width\n",
" \n",
" # Give higher reward if the car is closer to center line and vice versa\n",
" if distance_from_center <= marker_1:\n",
" reward = 1.0\n",
" elif distance_from_center <= marker_2:\n",
" reward = 0.5\n",
" elif distance_from_center <= marker_3:\n",
" reward = 0.1\n",
" else:\n",
" reward = 1e-3 # likely crashed/ close to off track\n",
" \n",
" return float(reward)\n",
"```"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 2\n",
"- Time trial - stay inside the two borders\n",
"```python3\n",
"def reward_function(params):\n",
" '''\n",
" Example of rewarding the agent to stay inside the two borders of the track\n",
" '''\n",
" \n",
" # Read input parameters\n",
" all_wheels_on_track = params['all_wheels_on_track']\n",
" distance_from_center = params['distance_from_center']\n",
" track_width = params['track_width']\n",
" \n",
" # Give a very low reward by default\n",
" reward = 1e-3\n",
"\n",
" # Give a high reward if no wheels go off the track and\n",
" # the agent is somewhere in between the track borders\n",
" if all_wheels_on_track and (0.5*track_width - distance_from_center) >= 0.05:\n",
" reward = 1.0\n",
"\n",
" # Always return a float value\n",
" return float(reward)\n",
"```"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 3\n",
"- Time trial - prevent zig-zag\n",
"```python3\n",
"def reward_function(params):\n",
" '''\n",
" Example of penalize steering, which helps mitigate zig-zag behaviors\n",
" '''\n",
"\n",
" # Read input parameters\n",
" distance_from_center = params['distance_from_center']\n",
" track_width = params['track_width']\n",
" abs_steering = abs(params['steering_angle']) # Only need the absolute steering angle\n",
"\n",
" # Calculate 3 marks that are farther and father away from the center line\n",
" marker_1 = 0.1 * track_width\n",
" marker_2 = 0.25 * track_width\n",
" marker_3 = 0.5 * track_width\n",
"\n",
" # Give higher reward if the car is closer to center line and vice versa\n",
" if distance_from_center <= marker_1:\n",
" reward = 1.0\n",
" elif distance_from_center <= marker_2:\n",
" reward = 0.5\n",
" elif distance_from_center <= marker_3:\n",
" reward = 0.1\n",
" else:\n",
" reward = 1e-3 # likely crashed/ close to off track\n",
"\n",
" # Steering penality threshold, change the number based on your action space setting\n",
" ABS_STEERING_THRESHOLD = 15 \n",
" \n",
" # Penalize reward if the car is steering too much\n",
" if abs_steering > ABS_STEERING_THRESHOLD:\n",
" reward *= 0.8\n",
" return float(reward)\n",
"```"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 4\n",
"- Object avoidance and head-to-head - stay on one lane and not crashing (default for OA and h2h)\n",
"- [Link](https://docs.aws.amazon.com/deepracer/latest/developerguide/deepracer-reward-function-examples.html#deepracer-reward-function-example-3)\n",
"```python3\n",
"import math\n",
"def reward_function(params):\n",
" '''\n",
" Example of rewarding the agent to stay inside two borders\n",
" and penalizing getting too close to the objects in front\n",
" '''\n",
" all_wheels_on_track = params['all_wheels_on_track']\n",
" distance_from_center = params['distance_from_center']\n",
" track_width = params['track_width']\n",
" objects_location = params['objects_location']\n",
" agent_x = params['x']\n",
" agent_y = params['y']\n",
" _, next_object_index = params['closest_objects']\n",
" objects_left_of_center = params['objects_left_of_center']\n",
" is_left_of_center = params['is_left_of_center']\n",
" # Initialize reward with a small number but not zero\n",
" # because zero means off-track or crashed\n",
" reward = 1e-3\n",
" # Reward if the agent stays inside the two borders of the track\n",
" if all_wheels_on_track and (0.5 * track_width - distance_from_center) >= 0.05:\n",
" reward_lane = 1.0\n",
" else:\n",
" reward_lane = 1e-3\n",
" # Penalize if the agent is too close to the next object\n",
" reward_avoid = 1.0\n",
" # Distance to the next object\n",
" next_object_loc = objects_location[next_object_index]\n",
" distance_closest_object = math.sqrt((agent_x - next_object_loc[0])**2 + (agent_y - next_object_loc[1])**2)\n",
" # Decide if the agent and the next object is on the same lane\n",
" is_same_lane = objects_left_of_center[next_object_index] == is_left_of_center\n",
" if is_same_lane:\n",
" if 0.5 <= distance_closest_object < 0.8:\n",
" reward_avoid *= 0.5\n",
" elif 0.3 <= distance_closest_object < 0.5:\n",
" reward_avoid *= 0.2\n",
" elif distance_closest_object < 0.3:\n",
" reward_avoid = 1e-3 # Likely crashed\n",
" # Calculate reward by putting different weights on\n",
" # the two aspects above\n",
" reward += 1.0 * reward_lane + 4.0 * reward_avoid\n",
" return reward\n",
"```"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}