Add sources for some strategies.

axelrod/strategies/alternator.py

@@ -5,7 +5,13 @@
 
 
 class Alternator(Player):
-    """A player who alternates between cooperating and defecting."""
+    """
+    A player who alternates between cooperating and defecting.
+
+    Names
+
+    - Alternator: [Bendor1993]_
+    """
 
     name = 'Alternator'
     classifier = {

axelrod/strategies/ann.py

@@ -1,9 +1,3 @@
-"""Artificial Neural Network based strategy.
-
-# Original Source: https://gist.github.com/mojones/550b32c46a8169bb3cd89d917b73111a#file-ann-strategy-test-L60
-# Original Author: Martin Jones, @mojones
-"""
-
 import numpy as np
 
 from axelrod.actions import Actions, Action
@@ -146,7 +140,9 @@ def split_weights(weights: List[float], num_features: int, num_hidden: int) -> T
 
 
 class ANN(Player):
-    """A single layer neural network based strategy, with the following
+    """Artificial Neural Network based strategy.
+
+    A single layer neural network based strategy, with the following
     features:
     * Opponent's first move is C
     * Opponent's first move is D
@@ -165,6 +161,13 @@ class ANN(Player):
     * Total player cooperations
     * Total player defections
     * Round number
+
+    Original Source: https://gist.github.com/mojones/550b32c46a8169bb3cd89d917b73111a#file-ann-strategy-test-L60
+
+
+    Names
+
+    - Artificial Neural Network based strategy: Original name by Martin Jones
     """
     name = 'ANN'
     classifier = {

axelrod/strategies/apavlov.py

@@ -6,13 +6,14 @@
 
 class APavlov2006(Player):
     """
-    APavlov as defined in http://www.cs.nott.ac.uk/~pszjl/index_files/chapter4.pdf
-    (pages 10-11).
-
     APavlov attempts to classify its opponent as one of five strategies:
     Cooperative, ALLD, STFT, PavlovD, or Random. APavlov then responds in a
     manner intended to achieve mutual cooperation or to defect against
     uncooperative opponents.
+
+    Names:
+
+    - Adaptive Pavlov 2006: [Li2007]_
     """
 
     name = "Adaptive Pavlov 2006"
@@ -73,13 +74,14 @@ def reset(self):
 
 class APavlov2011(Player):
     """
-    APavlov as defined in http://www.graham-kendall.com/papers/lhk2011.pdf, as
-    closely as can be determined.
-
     APavlov attempts to classify its opponent as one of four strategies:
     Cooperative, ALLD, STFT, or Random. APavlov then responds in a manner
     intended to achieve mutual cooperation or to defect against
     uncooperative opponents.
+
+    Names:
+
+    - Adaptive Pavlov 2007: [Li2011]_
     """
 
     name = "Adaptive Pavlov 2011"

axelrod/strategies/appeaser.py

@@ -9,6 +9,10 @@ class Appeaser(Player):
 
     Switch the classifier every time the opponent plays 'D'.
     Start with 'C', switch between 'C' and 'D' when opponent plays 'D'.
+
+    Names:
+
+    - Appeaser: Original Name by Jochen Müller
     """
 
     name = 'Appeaser'

axelrod/strategies/averagecopier.py

@@ -9,6 +9,10 @@ class AverageCopier(Player):
     """
     The player will cooperate with probability p if the opponent's cooperation
     ratio is p. Starts with random decision.
+
+    Names:
+
+    - Average Copier: Original name by Geraint Palmer
     """
 
     name = 'Average Copier'
@@ -31,7 +35,13 @@ def strategy(self, opponent: Player) -> Action:
 
 
 class NiceAverageCopier(Player):
-    """Same as Average Copier, but always starts by cooperating."""
+    """
+    Same as Average Copier, but always starts by cooperating.
+
+    Names:
+
+    - Average Copier: Original name by Owen Campbell
+    """
 
     name = 'Nice Average Copier'
     classifier = {

axelrod/strategies/backstabber.py

@@ -10,6 +10,10 @@ class BackStabber(Player):
     """
     Forgives the first 3 defections but on the fourth
     will defect forever. Defects on the last 2 rounds unconditionally.
+
+    Names:
+
+    - Backstabber: Original name by Thomas Campbell
     """
 
     name = 'BackStabber'
@@ -36,6 +40,10 @@ class DoubleCrosser(Player):
     If 8 <= current round <= 180,
     if the opponent did not defect in the first 7 rounds,
     the player will only defect after the opponent has defected twice in-a-row.
+
+    Names:
+
+    - Double Crosser: Original name by Thomas Campbell
     """
 
     name = 'DoubleCrosser'

axelrod/strategies/calculator.py

@@ -10,6 +10,11 @@ class Calculator(Player):
     """
     Plays like (Hard) Joss for the first 20 rounds. If periodic behavior is
     detected, defect forever. Otherwise play TFT.
+
+
+    Names:
+
+    - Calculator: Original name by Marc Harper
     """
 
     name = "Calculator"

axelrod/strategies/cooperator.py

@@ -5,7 +5,12 @@
 
 
 class Cooperator(Player):
-    """A player who only ever cooperates."""
+    """A player who only ever cooperates.
+
+    Names:
+
+    - Cooperator: [Axelrod1984]_
+    """
 
     name = 'Cooperator'
     classifier = {
@@ -24,7 +29,13 @@ def strategy(opponent: Player) -> Action:
 
 
 class TrickyCooperator(Player):
-    """A cooperator that is trying to be tricky."""
+    """
+    A cooperator that is trying to be tricky.
+
+    Names:
+
+    - Tricky Cooperator: Original name by Karol Langner
+    """
 
     name = "Tricky Cooperator"
     classifier = {

axelrod/strategies/cycler.py

@@ -11,6 +11,10 @@ class AntiCycler(Player):
     """
     A player that follows a sequence of plays that contains no cycles:
     CDD  CD  CCD CCCD CCCCD ...
+
+    Names:
+
+    - Anti Cycler: Original name by Marc Harper
     """
 
     name = 'AntiCycler'
@@ -53,7 +57,13 @@ def reset(self):
 
 
 class Cycler(Player):
-    """A player that repeats a given sequence indefinitely."""
+    """
+    A player that repeats a given sequence indefinitely.
+
+    Names:
+
+    - Cycler: Original name by Marc Harper
+    """
 
     name = 'Cycler'
     classifier = {
@@ -94,7 +104,13 @@ def reset(self):
 
 
 class CyclerDC(Cycler):
+    """
+    Cycles D, C
 
+    Names:
+
+    - Cycler DC: Original name by Marc Harper
+    """
     name = 'Cycler DC'
     classifier = copy.copy(Cycler.classifier)
     classifier['memory_depth'] = 1
@@ -104,7 +120,13 @@ def __init__(self) -> None:
 
 
 class CyclerCCD(Cycler):
+    """
+    Cycles C, C, D
 
+    Names:
+
+    - Cycler CCD: Original name by Marc Harper
+    """
     name = 'Cycler CCD'
     classifier = copy.copy(Cycler.classifier)
     classifier['memory_depth'] = 2
@@ -114,7 +136,13 @@ def __init__(self) -> None:
 
 
 class CyclerDDC(Cycler):
+    """
+    Cycles D, D, C
 
+    Names:
+
+    - Cycler DDC: Original name by Marc Harper
+    """
     name = 'Cycler DDC'
     classifier = copy.copy(Cycler.classifier)
     classifier['memory_depth'] = 2
@@ -124,7 +152,13 @@ def __init__(self) -> None:
 
 
 class CyclerCCCD(Cycler):
+    """
+    Cycles C, C, C, D
 
+    Names:
+
+    - Cycler CCCD: Original name by Marc Harper
+    """
     name = 'Cycler CCCD'
     classifier = copy.copy(Cycler.classifier)
     classifier['memory_depth'] = 3
@@ -134,7 +168,13 @@ def __init__(self) -> None:
 
 
 class CyclerCCCCCD(Cycler):
+    """
+    Cycles C, C, C, C, C, D
 
+    Names:
+
+    - Cycler CCCD: Original name by Marc Harper
+    """
     name = 'Cycler CCCCCD'
     classifier = copy.copy(Cycler.classifier)
     classifier['memory_depth'] = 5
@@ -144,6 +184,13 @@ def __init__(self) -> None:
 
 
 class CyclerCCCDCD(Cycler):
+    """
+    Cycles C, C, C, D, C, D
+
+    Names:
+
+    - Cycler CCCDCD: Original name by Marc Harper
+    """
 
     name = 'Cycler CCCDCD'
     classifier = copy.copy(Cycler.classifier)

axelrod/strategies/darwin.py

@@ -10,20 +10,25 @@
 
 
 class Darwin(Player):
-    """ A strategy which accumulates a record (the 'genome') of what the most
-        favourable response in the previous round should have been, and naively
-        assumes that this will remain the correct response at the same round of
-        future trials.
+    """
+    A strategy which accumulates a record (the 'genome') of what the most
+    favourable response in the previous round should have been, and naively
+    assumes that this will remain the correct response at the same round of
+    future trials.
+
+    This 'genome' is preserved between opponents, rounds and repetitions of
+    the tournament.  It becomes a characteristic of the type and so a single
+    version of this is shared by all instances for each loading of the class.
+
+    As this results in information being preserved between tournaments, this
+    is classified as a cheating strategy!
 
-        This 'genome' is preserved between opponents, rounds and repetitions of
-        the tournament.  It becomes a characteristic of the type and so a single
-        version of this is shared by all instances for each loading of the class.
+    If no record yet exists, the opponent's response from the previous round
+    is returned.
 
-        As this results in information being preserved between tournaments, this
-        is classified as a cheating strategy!
+    Names:
 
-        If no record yet exists, the opponent's response from the previous round
-        is returned.
+    - Darwin: Original name by Paul Slavin
     """
 
     name = "Darwin"

docs/reference/bibliography.rst

@@ -17,16 +17,17 @@ documentation.
 .. [Au2006] Au, T.-C. and  Nau, D. S. (2006) Accident or intention: That is the question (in the iterated prisoner’s dilemma). In Proc. Int. Conf. Auton. Agents and Multiagent Syst. (AAMAS), pp. 561–568. http://www.cs.umd.edu/~nau/papers/au2006accident.pdf
 .. [Axelrod1980] Axelrod, R. (1980). Effective Choice in the Prisoner’s Dilemma. Journal of Conflict Resolution, 24(1), 3–25.
 .. [Axelrod1980b] Axelrod, R. (1980). More Effective Choice in the Prisoner’s Dilemma. Journal of Conflict Resolution, 24(3), 379-403.
-.. [Axelrod1984]  The Evolution of Cooperation. Basic Books. ISBN 0-465-02121-2.
+.. [Axelrod1984] The Evolution of Cooperation. Basic Books. ISBN 0-465-02121-2.
 .. [Axelrod1995] Wu, J. and Axelrod, R. (1995). How to cope with noise in the Iterated prisoner’s dilemma, Journal of Conflict Resolution, 39(1), pp. 183–189. doi: 10.1177/0022002795039001008.
 .. [Banks1980] Banks, J. S., & Sundaram, R. K. (1990). Repeated games, finite automata, and complexity. Games and Economic Behavior, 2(2), 97–117.  http://doi.org/10.1016/0899-8256(90)90024-O
-.. [Bendor1993] Bendor, Jonathan, et al. “Cooperation Under Uncertainty: What Is New, What Is True, and What Is Important.” American Sociological Review, vol. 61, no. 2, 1996, pp. 333–338., www.jstor.org/stable/2096337.
+.. [Bendor1993] Bendor, Jonathan. "Uncertainty and the Evolution of Cooperation." The Journal of Conflict Resolution, 37(4), 709–734.
 .. [Beaufils1997] Beaufils, B. and Delahaye, J. (1997). Our Meeting With Gradual: A Good Strategy For The Iterated Prisoner’s Dilemma. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.4041
 .. [Berg2015] Berg, P. Van Den, & Weissing, F. J. (2015). The importance of mechanisms for the evolution of cooperation. Proceedings of the Royal Society B-Biological Sciences, 282.
 .. [Frean1994] Frean, Marcus R. “The Prisoner's Dilemma without Synchrony.” Proceedings: Biological Sciences, vol. 257, no. 1348, 1994, pp. 75–79. www.jstor.org/stable/50253.
 .. [Hilde2013] Hilbe, C., Nowak, M.A. and Traulsen, A. (2013). Adaptive dynamics of extortion and compliance, PLoS ONE, 8(11), p. e77886. doi: 10.1371/journal.pone.0077886.
 .. [Kraines1989] Kraines, D. & Kraines, V. Theor Decis (1989) 26: 47.  doi:10.1007/BF00134056
 .. [LessWrong2011] Zoo of Strategies (2011) LessWrong. Available at: http://lesswrong.com/lw/7f2/prisoners_dilemma_tournament_results/
+.. [Li2007] Li, J, How to Design a Strategy to Win an IPD Tournament, in Kendall G., Yao X. and Chong S. (eds.) The iterated prisoner’s dilemma: 20 years on. World Scientific, chapter 4, pp. 29-40, 2007.
 .. [Li2009] Li, J. & Kendall, G. (2009). A Strategy with Novel Evolutionary Features for the Iterated Prisoner’s Dilemma. Evolutionary Computation 17(2): 257–274.
 .. [Li2011] Li, J., Hingston, P., Member, S., & Kendall, G. (2011). Engineering Design of Strategies for Winning Iterated Prisoner ’ s Dilemma Competitions, 3(4), 348–360.
 .. [Li2016] Li, J. and Kendall, G. (2016). The Effect of Memory Size on the Evolutionary Stability of Strategies in Iterated Prisoner's Dilemma. IEEE Transactions on Evolutionary Computation, 18(6) 819-826