Skip to Main Content
Table 2:
Example Policy Evaluation.
Step 2
Cost (nats)Cost (nats)
ActionSquare ColorTarget ProximityActionSquare ColorTarget Proximity
Stay at (2,8) -+4.2 Up to (2,7) -+3.6 
   Down to (2,8) -+4.2 
   Left to (1,8) ++5.0 
   Right to (3,8) ++3.6 
   Stay at (2,8) -+4.2 
Up to (2,7) -+3.6 Up to (2,6) ++2.2 
   Down to (2,8) -+4.2 
   Left to (1,7) ++4.4 
   Right to (3,7) -+2.8 
   Stay at (2,7) -+3.6 
Down to (2,8) -+4.2 Up to (2,7) -+3.6 
   Down to (2,8) -+4.2 
   Left to (1,8) ++5.0 
   Right to (3,8) ++3.6 
   Stay at (2,8) -+4.2 
Left to (1,8) ++5.0 Up to (1,7) ++4.4 
   Down to (1,8) ++5.0 
   Left to (1,8) ++5.0 
   Right to (2,8) -+4.2 
   Stay at (1,8) ++5.0 
Right to (3,8) ++2.8 Up to (3,7) -+2.8 
   Down to (3,8) ++3.6 
   Left to (2,8) -+4.2 
   Right to (4,8) -+4.2 
   Stay at (3,8) ++2.8 
Step 2
Cost (nats)Cost (nats)
ActionSquare ColorTarget ProximityActionSquare ColorTarget Proximity
Stay at (2,8) -+4.2 Up to (2,7) -+3.6 
   Down to (2,8) -+4.2 
   Left to (1,8) ++5.0 
   Right to (3,8) ++3.6 
   Stay at (2,8) -+4.2 
Up to (2,7) -+3.6 Up to (2,6) ++2.2 
   Down to (2,8) -+4.2 
   Left to (1,7) ++4.4 
   Right to (3,7) -+2.8 
   Stay at (2,7) -+3.6 
Down to (2,8) -+4.2 Up to (2,7) -+3.6 
   Down to (2,8) -+4.2 
   Left to (1,8) ++5.0 
   Right to (3,8) ++3.6 
   Stay at (2,8) -+4.2 
Left to (1,8) ++5.0 Up to (1,7) ++4.4 
   Down to (1,8) ++5.0 
   Left to (1,8) ++5.0 
   Right to (2,8) -+4.2 
   Stay at (1,8) ++5.0 
Right to (3,8) ++2.8 Up to (3,7) -+2.8 
   Down to (3,8) ++3.6 
   Left to (2,8) -+4.2 
   Right to (4,8) -+4.2 
   Stay at (3,8) ++2.8 
Close Modal

or Create an Account

Close Modal
Close Modal