Timeline for Does an RL agent still learn if its actions are "blocked"?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 30, 2019 at 9:03 | comment | added | Neil Slater | I would add that it is usually not necessary to add such a negative reward, if there is already a consequence for using a time step. E.g. in a maze, the reward is typically -1 per time step. Taking an action that causes no movement will quickly be leanred away with no special handling. The stock trading example might be different as there is presumably a deliberate "wait" action, and you don't want the agent to force itself to wait by proxy of choosing non-valid actions that may in slightly different circumstances become valid and cause extreme behaviour (like selling all stock). | |
| Jul 30, 2019 at 8:07 | comment | added | PyRsquared | That makes intuitive sense. Thanks! | |
| Jul 30, 2019 at 8:07 | vote | accept | PyRsquared | ||
| Jul 30, 2019 at 7:08 | history | answered | Sean Mirchi | CC BY-SA 4.0 |