You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the description it reads:
The agent can perform one of four actions,
up, down, left or right, which have a stochastic effect. With probability 2/3, the actions
cause the agent to move one cell in the corresponding direction, and with probability 1/3,
the agent moves instead in one of the other three directions, each with 1/9 probability. In
either case, if the movement would take the agent into a wall then the agent remains in the
same cell.
However, if I understand the code correctly, the self.currentcell is set to be the next cell before the random process happens. Therefore the agent will land in next cell with prob 2/3, which is correct, but with prob 1/3 it will land in the neighboring cells of the nextcell (equivalent to taking an additional step). That doesn't seem to fit the description above and in the paper.
The text was updated successfully, but these errors were encountered:
In the description it reads:
The agent can perform one of four actions,
up, down, left or right, which have a stochastic effect. With probability 2/3, the actions
cause the agent to move one cell in the corresponding direction, and with probability 1/3,
the agent moves instead in one of the other three directions, each with 1/9 probability. In
either case, if the movement would take the agent into a wall then the agent remains in the
same cell.
However, if I understand the code correctly, the self.currentcell is set to be the next cell before the random process happens. Therefore the agent will land in next cell with prob 2/3, which is correct, but with prob 1/3 it will land in the neighboring cells of the nextcell (equivalent to taking an additional step). That doesn't seem to fit the description above and in the paper.
The text was updated successfully, but these errors were encountered: