Update README.md
This commit is contained in:
@@ -5,6 +5,6 @@ that learn from the environment based on a defined cost function.
|
|||||||
|
|
||||||
#### Upcoming objectives
|
#### Upcoming objectives
|
||||||
1. Verify again that sweep interpolation data provides reasonable estimates of real-world forces and torques using load cell
|
1. Verify again that sweep interpolation data provides reasonable estimates of real-world forces and torques using load cell
|
||||||
2. Implement PID controller that interfaces with the simulation environment present in ```lev_env.py```
|
2. Implement PID controller that interfaces with the simulation environment present in ```lev_pod_env.py```
|
||||||
3. Implement other forms of reinforcement learning control, look into designing a reward structure that is conducive to learning, and
|
3. Implement other forms of reinforcement learning control, look into designing a reward structure that is conducive to learning, and
|
||||||
overall dive into more research on reinforcement learning algorithms for very sensitive tasks that are intrinsically highly unstable.
|
overall dive into more research on reinforcement learning algorithms for very sensitive tasks that are intrinsically highly unstable.
|
||||||
|
|||||||
Reference in New Issue
Block a user