A Reinforcement Learning library that act as an abstraction layer between different simulation environments and languages, allowing for simulator & code agnostic reinforcement learning research to be done.
This might be too abstract or language dependent and could be done easier + more efficient. E.g. think of a Robotic arm, where we should be able to describe each join independently.
Current thinking is to go deeper and work on a Digital Twin representation that can be used to call the RL algorithms on top of this. Hierarchy is thus important. A good example of how to make such a flow chart can be found at: https://alyssax.com/x/flowy/
Current thinking is to go deeper and work on a Digital Twin representation that can be used to call the RL algorithms on top of this. Hierarchy is thus important
Currently we can describe a state as shown before:
Tuple([ Box(0, 255, shape=(64, 64, 3)), Box(-50, 50, shape=(3, )) ])
This might be too abstract or language dependent and could be done easier + more efficient. E.g. think of a Robotic arm, where we should be able to describe each join independently.
Current thinking is to go deeper and work on a
Digital Twin
representation that can be used to call the RL algorithms on top of this. Hierarchy is thus important. A good example of how to make such a flow chart can be found at: https://alyssax.com/x/flowy/