Skip to Main Content

To begin with, in Table 5, we present a categorization of NEAT's successors based on the employed encoding scheme, that is, the way the mapping between GA's genotype and ANN's phenotype happens. We identify three types of encoding: direct, indirect, and hybrid.

Table 4:
Quality scores of selected studies.
StudyRefScoreStudyRefScore
1. Coevolutionary NEAT (Stanley and Miikkulainen, 2004) 0.92 32. Adaptive ES-HyperNEAT (Risi and Stanley, 2012b) 0.65 
2. ModularNEAT (Reisinger et al., 2004) 0.81 33. NEATfields (Inden et al., 2012) 0.92 
3. FS-NEAT (Whiteson et al., 2005) 0.81 34. SNAP-NEAT (Kohl and Miikkulainen, 2012) 0.81 
4. rtNEAT (Stanley et al., 2005) 0.71 35. SUPG-HyperNEAT (Morse et al., 2013) 0.85 
5. rtNEATv2 (D'Silva et al., 2005) 0.73 36. MSS-HyperNEAT (Pugh and Stanley, 2013) 0.85 
6. CPPN-NEAT (Stanley, 2006) 0.58 37. Adaptive HyperNEATv2 (Gallego-Durán et al., 2013) 0.58 
7. (Online-) NEAT+Q (Whiteson and Stone, 2006a) 0.81 38. NEAR (Chatzidimitriou and Mitkas, 2013) 0.88 
8. LAPCA-NEAT (Monroy et al., 2006) 0.65 39. Layered NEAT (Wang et al., 2013) 0.62 
9. L-NEAT (Chen and Alahakoon, 2006) 0.54 40. FNS-NEATFields (Inden et al., 2013) 0.88 
10. nnrg.hazel (Reisinger et al., 2007) 0.65 41. Phased NEAT (Tan et al., 2013) 0.77 
11. KO-NEAT (Zhao et al., 2007) 0.62 42. HyperNEAT-CCT (Huizinga et al., 2014) 0.85 
12. NEAT-CTRNN (Miguel et al., 2008) 0.69 43. Seeded (Adaptive) HyperNEAT (Risi and Stanley, 2014) 0.69 
13. HyperNEAT (Stanley et al., 2009) 0.85 44. NS-FE-CPPN-NEAT (Methenitis et al., 2015) 0.62 
14. TL-CPPN-NEAT (Bahçeci and Miikkulainen, 2008) 0.69 45. Deep HyperNEAT (Verbancsics and Harguess, 2015) 0.77 
15. Multiagent HyperNEAT (D'Ambrosio and Stanley, 2008) 0.92 46. PIGEON (Stein et al., 2015) 0.85 
16. cgNEAT (Hastings et al., 2009) 0.54 47. PFS-NEAT (Loscalzo et al., 2015) 0.81 
17. RL-SANE (Wright and Gemelli, 2009) 0.62 48. odNEAT (Silva et al., 2015) 0.92 
18. FD-NEAT (Tan et al., 2009) 0.81 49. odNEATv2 (Silva et al., 2016) 0.92 
19. RBF/Cascade-NEAT (Kohl and Miikkulainen, 2009) 0.81 50. τ-NEAT (Caamaño et al., 2016) 0.73 
20. MO-NEAT (Haggett and Chu, 2009) 0.73 51. MAP-Elites CPPN (Tarapore et al., 2016) 0.73 
21. Adaptive HyperNEAT (Risi and Stanley, 2010) 0.73 52. NEAT-LSTM, NEAT-LSTM-IM (Rawal and Miikkulainen, 2016) 0.73 
22. Online (rt-) NEAT (Cardamone et al., 2010) 0.85 53. MM-NEAT (Schrum and Miikkulainen, 2016) 0.83 
23. Recurrent CPPN-NEAT (Auerbach and Bongard, 2011) 0.85 54. MB-HyperNEAT (Schrum et al., 2016) 0.81 
24. Multiagent HyperNEATv2 (D'Ambrosio et al., 2011) 0.77 55. PLPS-NEAT-TL (Hardwick-Smith et al., 2017) 0.79 
25. HyperNEAT-LEO (Verbancsics and Stanley, 2011) 0.85 56. TMO-NEAT (Marzullo et al., 2017) 0.75 
26. IFSE-NEAT (Wright et al., 2012) 0.57 57. τ-HyperNEAT (Silva et al., 2017) 0.58 
27. NoveltyNEAT (Lehman and Stanley, 2011a) 0.88 58. EXACT (Desell, 2017a) 0.63 
28. SwitchHybrID (Clune et al., 2011) 0.85 59. HA-NEAT (Hagg et al., 2017) 0.90 
29. MFF-NEAT (Manning and Walsh, 2012) 0.62 60. NEAT-RAC-PGS (Peng et al., 2017) 0.88 
30. ES-HyperNEAT(-LEO) (Risi and Stanley, 2012a) 0.92 61. NEAT-FLEX (Grisci and Dorn, 2017) 0.58 
31. DynNEAT (Krčah, 2012) 0.73    
StudyRefScoreStudyRefScore
1. Coevolutionary NEAT (Stanley and Miikkulainen, 2004) 0.92 32. Adaptive ES-HyperNEAT (Risi and Stanley, 2012b) 0.65 
2. ModularNEAT (Reisinger et al., 2004) 0.81 33. NEATfields (Inden et al., 2012) 0.92 
3. FS-NEAT (Whiteson et al., 2005) 0.81 34. SNAP-NEAT (Kohl and Miikkulainen, 2012) 0.81 
4. rtNEAT (Stanley et al., 2005) 0.71 35. SUPG-HyperNEAT (Morse et al., 2013) 0.85 
5. rtNEATv2 (D'Silva et al., 2005) 0.73 36. MSS-HyperNEAT (Pugh and Stanley, 2013) 0.85 
6. CPPN-NEAT (Stanley, 2006) 0.58 37. Adaptive HyperNEATv2 (Gallego-Durán et al., 2013) 0.58 
7. (Online-) NEAT+Q (Whiteson and Stone, 2006a) 0.81 38. NEAR (Chatzidimitriou and Mitkas, 2013) 0.88 
8. LAPCA-NEAT (Monroy et al., 2006) 0.65 39. Layered NEAT (Wang et al., 2013) 0.62 
9. L-NEAT (Chen and Alahakoon, 2006) 0.54 40. FNS-NEATFields (Inden et al., 2013) 0.88 
10. nnrg.hazel (Reisinger et al., 2007) 0.65 41. Phased NEAT (Tan et al., 2013) 0.77 
11. KO-NEAT (Zhao et al., 2007) 0.62 42. HyperNEAT-CCT (Huizinga et al., 2014) 0.85 
12. NEAT-CTRNN (Miguel et al., 2008) 0.69 43. Seeded (Adaptive) HyperNEAT (Risi and Stanley, 2014) 0.69 
13. HyperNEAT (Stanley et al., 2009) 0.85 44. NS-FE-CPPN-NEAT (Methenitis et al., 2015) 0.62 
14. TL-CPPN-NEAT (Bahçeci and Miikkulainen, 2008) 0.69 45. Deep HyperNEAT (Verbancsics and Harguess, 2015) 0.77 
15. Multiagent HyperNEAT (D'Ambrosio and Stanley, 2008) 0.92 46. PIGEON (Stein et al., 2015) 0.85 
16. cgNEAT (Hastings et al., 2009) 0.54 47. PFS-NEAT (Loscalzo et al., 2015) 0.81 
17. RL-SANE (Wright and Gemelli, 2009) 0.62 48. odNEAT (Silva et al., 2015) 0.92 
18. FD-NEAT (Tan et al., 2009) 0.81 49. odNEATv2 (Silva et al., 2016) 0.92 
19. RBF/Cascade-NEAT (Kohl and Miikkulainen, 2009) 0.81 50. τ-NEAT (Caamaño et al., 2016) 0.73 
20. MO-NEAT (Haggett and Chu, 2009) 0.73 51. MAP-Elites CPPN (Tarapore et al., 2016) 0.73 
21. Adaptive HyperNEAT (Risi and Stanley, 2010) 0.73 52. NEAT-LSTM, NEAT-LSTM-IM (Rawal and Miikkulainen, 2016) 0.73 
22. Online (rt-) NEAT (Cardamone et al., 2010) 0.85 53. MM-NEAT (Schrum and Miikkulainen, 2016) 0.83 
23. Recurrent CPPN-NEAT (Auerbach and Bongard, 2011) 0.85 54. MB-HyperNEAT (Schrum et al., 2016) 0.81 
24. Multiagent HyperNEATv2 (D'Ambrosio et al., 2011) 0.77 55. PLPS-NEAT-TL (Hardwick-Smith et al., 2017) 0.79 
25. HyperNEAT-LEO (Verbancsics and Stanley, 2011) 0.85 56. TMO-NEAT (Marzullo et al., 2017) 0.75 
26. IFSE-NEAT (Wright et al., 2012) 0.57 57. τ-HyperNEAT (Silva et al., 2017) 0.58 
27. NoveltyNEAT (Lehman and Stanley, 2011a) 0.88 58. EXACT (Desell, 2017a) 0.63 
28. SwitchHybrID (Clune et al., 2011) 0.85 59. HA-NEAT (Hagg et al., 2017) 0.90 
29. MFF-NEAT (Manning and Walsh, 2012) 0.62 60. NEAT-RAC-PGS (Peng et al., 2017) 0.88 
30. ES-HyperNEAT(-LEO) (Risi and Stanley, 2012a) 0.92 61. NEAT-FLEX (Grisci and Dorn, 2017) 0.58 
31. DynNEAT (Krčah, 2012) 0.73    
Table 5:
Encoding used by each method.
Direct Encoding (Stanley and Miikkulainen, 2002b, 2004; Reisinger et al., 2004; Whiteson et al., 2005; Stanley et al., 2005; D'Silva et al., 2005; Stanley, 2006; Whiteson and Stone, 2006a; Monroy et al., 2006; Chen and Alahakoon, 2006; Reisinger et al., 2007; Zhao et al., 2007; Miguel et al., 2008; Bahçeci and Miikkulainen, 2008; Hastings et al., 2009; Wright and Gemelli, 2009; Tan et al., 2009; Kohl and Miikkulainen, 2009; Haggett and Chu, 2009; Cardamone et al., 2010; Auerbach and Bongard, 2011; Wright et al., 2012; Lehman and Stanley, 2011a; Manning and Walsh, 2012; Krčah, 2012; Kohl and Miikkulainen, 2012; Chatzidimitriou and Mitkas, 2013; Wang et al., 2013; Inden et al., 2013; Tan et al., 2013; Methenitis et al., 2015; Stein et al., 2015; Loscalzo et al., 2015; Silva et al., 2015, 2016; Caamaño et al., 2016; Rawal and Miikkulainen, 2016; Schrum and Miikkulainen, 2016; Hardwick-Smith et al., 2017; Marzullo et al., 2017; Desell, 2017a; Hagg et al., 2017; Peng et al., 2017; Grisci and Dorn, 2017) 
Indirect Encoding (Stanley et al., 2009; D'Ambrosio and Stanley, 2008; Risi and Stanley, 2010; Auerbach and Bongard, 2011; D'Ambrosio et al., 2011; Verbancsics and Stanley, 2011; Risi and Stanley, 2012a, 2012b; Inden et al., 2012; Morse et al., 2013; Pugh and Stanley, 2013; Gallego-Durán et al., 2013; Huizinga et al., 2014; Risi and Stanley, 2014; Verbancsics and Harguess, 2015; Tarapore et al., 2016; Schrum et al., 2016; Silva et al., 2017) 
Hybrid (Clune et al., 2011) 
Direct Encoding (Stanley and Miikkulainen, 2002b, 2004; Reisinger et al., 2004; Whiteson et al., 2005; Stanley et al., 2005; D'Silva et al., 2005; Stanley, 2006; Whiteson and Stone, 2006a; Monroy et al., 2006; Chen and Alahakoon, 2006; Reisinger et al., 2007; Zhao et al., 2007; Miguel et al., 2008; Bahçeci and Miikkulainen, 2008; Hastings et al., 2009; Wright and Gemelli, 2009; Tan et al., 2009; Kohl and Miikkulainen, 2009; Haggett and Chu, 2009; Cardamone et al., 2010; Auerbach and Bongard, 2011; Wright et al., 2012; Lehman and Stanley, 2011a; Manning and Walsh, 2012; Krčah, 2012; Kohl and Miikkulainen, 2012; Chatzidimitriou and Mitkas, 2013; Wang et al., 2013; Inden et al., 2013; Tan et al., 2013; Methenitis et al., 2015; Stein et al., 2015; Loscalzo et al., 2015; Silva et al., 2015, 2016; Caamaño et al., 2016; Rawal and Miikkulainen, 2016; Schrum and Miikkulainen, 2016; Hardwick-Smith et al., 2017; Marzullo et al., 2017; Desell, 2017a; Hagg et al., 2017; Peng et al., 2017; Grisci and Dorn, 2017) 
Indirect Encoding (Stanley et al., 2009; D'Ambrosio and Stanley, 2008; Risi and Stanley, 2010; Auerbach and Bongard, 2011; D'Ambrosio et al., 2011; Verbancsics and Stanley, 2011; Risi and Stanley, 2012a, 2012b; Inden et al., 2012; Morse et al., 2013; Pugh and Stanley, 2013; Gallego-Durán et al., 2013; Huizinga et al., 2014; Risi and Stanley, 2014; Verbancsics and Harguess, 2015; Tarapore et al., 2016; Schrum et al., 2016; Silva et al., 2017) 
Hybrid (Clune et al., 2011) 

Close Modal

or Create an Account

Close Modal
Close Modal