Parsing for POMDP with state rewards fails

[TheGreatfpmK]

When parsing a POMDP with state rewards, the state rewards are ignored i.e. no reward model for state rewards is created, and the rewards (at least when parsing DRN) are parsed as state labels instead. For example, on this POMDP pomdp-state-rewards.zip I get following output after parsing:

Model type:     POMDP (sparse)
States:         16
Transitions:    26
Choices:        18
Observations:   5
Reward Models:  none
State Labels:   5 labels
   * deadlock -> 2 item(s)
   * [100] -> 2 item(s)
   * init -> 1 item(s)
   * done -> 2 item(s)
   * [0] -> 14 item(s)
Choice Labels:  5 labels
   * end -> 4 item(s)
   * eval -> 4 item(s)
   * roll2 -> 4 item(s)
   * roll1better -> 2 item(s)
   * roll1 -> 2 item(s)

as you can see the state rewards [100] and [0] were converted to state labels. It seems like there's a bug in the parser for POMDPs at least. I tried it with MDPs and there the state rewards are parsed correctly.