Timeline for How can we program Reinforcement learning without transition probability and rewards?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 1, 2018 at 15:40 | comment | added | numerairX | @RachelJung it makes sense and it is possible if you define to learn a transfer function, however keep in mind that the end goal of using reinforcement is get maximized long term reward, in this setting, if estimating parameters of transfer function helps the end goal, do it because you have a well defined expectation to maximize. However if you just want to estimate the probability distribution of the state transfer process, imo it should be done before you use this system. Hope that helps. | |
| Oct 1, 2018 at 15:26 | comment | added | Rachel | Thank you! In other words, for example, state A can transit to state B or state C, which we don't know exactly how often this transition to B or C from A. and We do online learning, which is learning the next state as the data comes in. The agent didn't know the state transition probability, but it will learn from experience that feedbacked from the environment, so the agent ends up learning its underlying transition probability as the value function of states. Does it make sense? | |
| Oct 1, 2018 at 14:34 | comment | added | numerairX | @RachelJung if I understand your question correctly, you mean if past state data is needed to determine next step of state right? If your states are sequential, say something like St = alpha*St-1, or robot moved to left or right following by up move etc, then yes we need to store the past states (but most likely only the latest one). | |
| Oct 1, 2018 at 14:11 | comment | added | Rachel | Thanks for answers!! from what you said at 2nd question, then do we need to store past states data to decide next state as sampling? | |
| Sep 28, 2018 at 19:40 | review | First posts | |||
| Sep 28, 2018 at 20:16 | |||||
| Sep 28, 2018 at 19:37 | history | answered | numerairX | CC BY-SA 4.0 |