Timeline for Reinforcement Learning with Adaptive Action Magnitude
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 14, 2018 at 22:04 | vote | accept | adnan jaffar | ||
| Dec 14, 2018 at 22:03 | history | edited | 50k4 | CC BY-SA 4.0 |
extended answer based on the comments
|
| Dec 14, 2018 at 21:53 | comment | added | adnan jaffar | Thank you for the perfect explanation. I got your point. | |
| Dec 14, 2018 at 21:45 | comment | added | 50k4 | You can also have a different parameter in the action execution which links action magnitude to the current state. e.g for a slow speed state apply less magnitude. This does not necessarily have to be in the Q table. | |
| Dec 14, 2018 at 21:43 | comment | added | 50k4 | As stated in point 2, the action does not have to be immediate and if it brings your environment to the same state in reality as in simulation it does not have to be the same implementation or it does not have to act in the same way. | |
| Dec 14, 2018 at 21:36 | comment | added | adnan jaffar | Can I make Q table like states * decision actions and decision actions are +1,-1. 1 means increase the previous action by some number and -1 decrease it by some number until i reach to next state. and I will update Q table only when i transition to next state. | |
| Dec 14, 2018 at 21:29 | comment | added | adnan jaffar | Yes, I still did not implement it in real but i am worried before implementation. My real environment is patient and so I can only try when I am confident about my algorithm. The virtual environment is somehow relating with real but not 100 percent. | |
| Dec 14, 2018 at 21:26 | comment | added | 50k4 | So you are training in a virtual environment (simulation) which does not reflect your real setup used in the expoitation? | |
| Dec 14, 2018 at 21:23 | comment | added | adnan jaffar | Ok thank you very much for a very nice explanation. Actually in my problem, I have finite states available (say 10). There are total 20 actions (say discrete value from 3 to 23). I know state 1 is bad and state 10 is good. In each state, i can only try few actions (not all 20). The problem actually lies here. When I do simulation, I know if I increase action by some number relative to previous action I will transition to next state. But In real implementation, it does not. Can I do like binary decisions (1 means keep increasing action and -1 keep decreasing until I transition to next state. | |
| Dec 14, 2018 at 13:13 | history | answered | 50k4 | CC BY-SA 4.0 |