add reference and docstrings

Author: yohm

axelrod/strategies/grudger.py

@@ -346,16 +346,20 @@ def strategy(opponent: Player) -> Action:
 
 class CAPRI(Player):
     """
-    CAPRI is a strategy whose behavior is defined by the following five rules.
-    C: Cooperate at mutual cooperation
-    A: Accept punishmentl
-    P: Punish
-    R: Recover
-    I: In all ohter cases, defect.
+    CAPRI is a memory-3 strategy proposed in [Murase2020]_. Its behavior is defined by the following five rules.
+    C: Cooperate at mutual cooperation.
+        This rule prescribes c at (ccc, ccc).
+    A: Accept punishment when you mistakenly defected from mutual cooperation.
+        This rule prescribes c at (ccd, ccc), (cdc, ccd), (dcc, cdc), and (ccc, dcc).
+    P: Punish your co-player by defecting once when he defected from mutual cooperation.
+        This rule prescribes d at (ccc, ccd), and then c at (ccd, cdc), (cdc, dcc), and (dcc, ccc).
+    R: Recover cooperation when you or your co-player cooperated at mutual defection.
+        This rule prescribes c at (ddd, ddc), (ddc, dcc), (dcc, ccc), (ddc, ddd), (dcc, ddc), (ccc, dcc), (ddc, ddc), and (dcc, dcc).
+    I: In all the ohter cases, defect.
 
     Names:
 
-    - CAPRI: Original Name by Y. Murase et al. [Murase 2020]
+    - CAPRI: Original Name by Y. Murase et al. [Murase2020]_
     """
 
     name = "CAPRI"
@@ -369,6 +373,7 @@ class CAPRI(Player):
     }
 
     def strategy(self, opponent: Player) -> Action:
+        # initial history profile is full cooperation
         hist = [[C,C],[C,C],[C,C]]
         for i in range(min(len(self.history), 3)):
             hist[-i-1][0] = self.history[-i-1]

docs/reference/bibliography.rst

@@ -46,6 +46,7 @@ documentation.
   for the Iterated Prisoner's Dilemma. Proceedings of the 2015
   International Conference on Autonomous Agents and Multiagent Systems.
 .. [Mittal2009] Mittal, S., & Deb, K. (2009). Optimal strategies of the iterated prisoner’s dilemma problem for multiple conflicting objectives. IEEE Transactions on Evolutionary Computation, 13(3), 554–565. https://doi.org/10.1109/TEVC.2008.2009459
+.. [Murase2020] Murase, Y., & Baek, S.K. (2020). Five Rules for Friendly Rivalry in Direct Reciprocity. Scientific Reports 10:16904 https://doi.org/10.1038/s41598-020-73855-x
 .. [Nachbar1992] Nachbar J., Evolution in the finitely repeated prisoner’s dilemma, Journal of Economic Behavior & Organization, 19(3): 307-326, 1992.
 .. [NC2019] https://github.com/ncase/trust (Accessed: 30 October 2019)
 .. [Nowak1989] Nowak, Martin, and Karl Sigmund. "Game-dynamical aspects of the prisoner's dilemma." Applied Mathematics and Computation 30.3 (1989): 191-213.