catanatron_gym.envs package#

Submodules#

catanatron_gym.envs.catanatron_env module#

class catanatron_gym.envs.catanatron_env.CatanatronEnv(config=None)#

Bases: Env

1v1 environment against a random player

reward_range#

-1 if player lost, 1 if player won, 0 otherwise.

action_space#

Integers from the [0, 289] interval. See Action Space table below.

observation_space#

Numeric Feature Vector. See Observation Space table below for quantities. They appear in vector in alphabetical order, from the perspective of “current” player (hiding/showing information accordingly). P0 is “current” player. P1 is next in line.

We use the following nomenclature for Tile ids and Node ids. Edge ids are self-describing (node-id, node-id) tuples. We also use Cube coordinates for tiles (see https://www.redblobgames.com/grids/hexagons/#coordinates)

Tile Ids Node Ids
Action Space#

Integer

Catanatron Action

0

(<ActionType.ROLL: ‘ROLL’>, None)

1

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (0, 0, 0))

2

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (1, -1, 0))

3

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (0, -1, 1))

4

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-1, 0, 1))

5

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-1, 1, 0))

6

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (0, 1, -1))

7

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (1, 0, -1))

8

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (2, -2, 0))

9

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (1, -2, 1))

10

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (0, -2, 2))

11

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-1, -1, 2))

12

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-2, 0, 2))

13

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-2, 1, 1))

14

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-2, 2, 0))

15

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (-1, 2, -1))

16

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (0, 2, -2))

17

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (1, 1, -2))

18

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (2, 0, -2))

19

(<ActionType.MOVE_ROBBER: ‘MOVE_ROBBER’>, (2, -1, -1))

20

(<ActionType.DISCARD: ‘DISCARD’>, None)

21

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (0, 5))

22

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (0, 1))

23

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (0, 20))

24

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (1, 2))

25

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (1, 6))

26

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (2, 3))

27

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (2, 9))

28

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (3, 4))

29

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (3, 12))

30

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (4, 5))

31

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (4, 15))

32

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (5, 16))

33

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (6, 7))

34

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (6, 23))

35

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (7, 8))

36

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (7, 24))

37

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (8, 9))

38

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (8, 27))

39

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (9, 10))

40

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (10, 11))

41

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (10, 29))

42

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (11, 12))

43

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (11, 32))

44

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (12, 13))

45

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (13, 14))

46

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (13, 34))

47

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (14, 15))

48

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (14, 37))

49

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (15, 17))

50

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (16, 18))

51

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (16, 21))

52

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (17, 18))

53

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (17, 39))

54

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (18, 40))

55

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (19, 21))

56

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (19, 20))

57

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (19, 46))

58

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (20, 22))

59

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (21, 43))

60

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (22, 23))

61

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (22, 49))

62

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (23, 52))

63

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (24, 25))

64

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (24, 53))

65

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (25, 26))

66

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (26, 27))

67

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (27, 28))

68

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (28, 29))

69

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (29, 30))

70

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (30, 31))

71

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (31, 32))

72

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (32, 33))

73

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (33, 34))

74

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (34, 35))

75

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (35, 36))

76

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (36, 37))

77

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (37, 38))

78

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (38, 39))

79

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (39, 41))

80

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (40, 42))

81

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (40, 44))

82

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (41, 42))

83

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (43, 44))

84

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (43, 47))

85

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (45, 47))

86

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (45, 46))

87

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (46, 48))

88

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (48, 49))

89

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (49, 50))

90

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (50, 51))

91

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (51, 52))

92

(<ActionType.BUILD_ROAD: ‘BUILD_ROAD’>, (52, 53))

93

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 0)

94

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 1)

95

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 2)

96

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 3)

97

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 4)

98

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 5)

99

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 6)

100

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 7)

101

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 8)

102

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 9)

103

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 10)

104

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 11)

105

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 12)

106

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 13)

107

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 14)

108

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 15)

109

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 16)

110

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 17)

111

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 18)

112

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 19)

113

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 20)

114

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 21)

115

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 22)

116

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 23)

117

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 24)

118

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 25)

119

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 26)

120

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 27)

121

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 28)

122

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 29)

123

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 30)

124

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 31)

125

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 32)

126

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 33)

127

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 34)

128

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 35)

129

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 36)

130

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 37)

131

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 38)

132

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 39)

133

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 40)

134

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 41)

135

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 42)

136

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 43)

137

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 44)

138

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 45)

139

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 46)

140

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 47)

141

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 48)

142

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 49)

143

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 50)

144

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 51)

145

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 52)

146

(<ActionType.BUILD_SETTLEMENT: ‘BUILD_SETTLEMENT’>, 53)

147

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 0)

148

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 1)

149

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 2)

150

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 3)

151

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 4)

152

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 5)

153

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 6)

154

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 7)

155

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 8)

156

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 9)

157

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 10)

158

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 11)

159

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 12)

160

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 13)

161

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 14)

162

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 15)

163

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 16)

164

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 17)

165

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 18)

166

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 19)

167

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 20)

168

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 21)

169

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 22)

170

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 23)

171

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 24)

172

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 25)

173

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 26)

174

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 27)

175

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 28)

176

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 29)

177

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 30)

178

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 31)

179

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 32)

180

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 33)

181

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 34)

182

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 35)

183

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 36)

184

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 37)

185

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 38)

186

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 39)

187

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 40)

188

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 41)

189

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 42)

190

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 43)

191

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 44)

192

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 45)

193

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 46)

194

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 47)

195

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 48)

196

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 49)

197

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 50)

198

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 51)

199

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 52)

200

(<ActionType.BUILD_CITY: ‘BUILD_CITY’>, 53)

201

(<ActionType.BUY_DEVELOPMENT_CARD: ‘BUY_DEVELOPMENT_CARD’>, None)

202

(<ActionType.PLAY_KNIGHT_CARD: ‘PLAY_KNIGHT_CARD’>, None)

203

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’, ‘WOOD’))

204

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’, ‘BRICK’))

205

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’, ‘SHEEP’))

206

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’, ‘WHEAT’))

207

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’, ‘ORE’))

208

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘BRICK’, ‘BRICK’))

209

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘BRICK’, ‘SHEEP’))

210

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘BRICK’, ‘WHEAT’))

211

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘BRICK’, ‘ORE’))

212

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘SHEEP’, ‘SHEEP’))

213

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘SHEEP’, ‘WHEAT’))

214

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘SHEEP’, ‘ORE’))

215

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WHEAT’, ‘WHEAT’))

216

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WHEAT’, ‘ORE’))

217

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘ORE’, ‘ORE’))

218

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WOOD’,))

219

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘BRICK’,))

220

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘SHEEP’,))

221

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘WHEAT’,))

222

(<ActionType.PLAY_YEAR_OF_PLENTY: ‘PLAY_YEAR_OF_PLENTY’>, (‘ORE’,))

223

(<ActionType.PLAY_ROAD_BUILDING: ‘PLAY_ROAD_BUILDING’>, None)

224

(<ActionType.PLAY_MONOPOLY: ‘PLAY_MONOPOLY’>, ‘WOOD’)

225

(<ActionType.PLAY_MONOPOLY: ‘PLAY_MONOPOLY’>, ‘BRICK’)

226

(<ActionType.PLAY_MONOPOLY: ‘PLAY_MONOPOLY’>, ‘SHEEP’)

227

(<ActionType.PLAY_MONOPOLY: ‘PLAY_MONOPOLY’>, ‘WHEAT’)

228

(<ActionType.PLAY_MONOPOLY: ‘PLAY_MONOPOLY’>, ‘ORE’)

229

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, ‘WOOD’, ‘BRICK’))

230

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, ‘WOOD’, ‘SHEEP’))

231

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, ‘WOOD’, ‘WHEAT’))

232

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, ‘WOOD’, ‘ORE’))

233

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, ‘BRICK’, ‘WOOD’))

234

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, ‘BRICK’, ‘SHEEP’))

235

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, ‘BRICK’, ‘WHEAT’))

236

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, ‘BRICK’, ‘ORE’))

237

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘WOOD’))

238

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘BRICK’))

239

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘WHEAT’))

240

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘SHEEP’, ‘ORE’))

241

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘WOOD’))

242

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘BRICK’))

243

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘SHEEP’))

244

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘WHEAT’, ‘ORE’))

245

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, ‘ORE’, ‘WOOD’))

246

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, ‘ORE’, ‘BRICK’))

247

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, ‘ORE’, ‘SHEEP’))

248

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, ‘ORE’, ‘WHEAT’))

249

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, None, ‘BRICK’))

250

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, None, ‘SHEEP’))

251

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, None, ‘WHEAT’))

252

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, ‘WOOD’, None, ‘ORE’))

253

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, None, ‘WOOD’))

254

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, None, ‘SHEEP’))

255

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, None, ‘WHEAT’))

256

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, ‘BRICK’, None, ‘ORE’))

257

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, None, ‘WOOD’))

258

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, None, ‘BRICK’))

259

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, None, ‘WHEAT’))

260

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, ‘SHEEP’, None, ‘ORE’))

261

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, None, ‘WOOD’))

262

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, None, ‘BRICK’))

263

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, None, ‘SHEEP’))

264

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, ‘WHEAT’, None, ‘ORE’))

265

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, None, ‘WOOD’))

266

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, None, ‘BRICK’))

267

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, None, ‘SHEEP’))

268

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, ‘ORE’, None, ‘WHEAT’))

269

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, None, None, ‘BRICK’))

270

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, None, None, ‘SHEEP’))

271

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, None, None, ‘WHEAT’))

272

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WOOD’, ‘WOOD’, None, None, ‘ORE’))

273

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, None, None, ‘WOOD’))

274

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, None, None, ‘SHEEP’))

275

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, None, None, ‘WHEAT’))

276

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘BRICK’, ‘BRICK’, None, None, ‘ORE’))

277

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, None, None, ‘WOOD’))

278

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, None, None, ‘BRICK’))

279

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, None, None, ‘WHEAT’))

280

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘SHEEP’, ‘SHEEP’, None, None, ‘ORE’))

281

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, None, None, ‘WOOD’))

282

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, None, None, ‘BRICK’))

283

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, None, None, ‘SHEEP’))

284

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘WHEAT’, ‘WHEAT’, None, None, ‘ORE’))

285

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, None, None, ‘WOOD’))

286

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, None, None, ‘BRICK’))

287

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, None, None, ‘SHEEP’))

288

(<ActionType.MARITIME_TRADE: ‘MARITIME_TRADE’>, (‘ORE’, ‘ORE’, None, None, ‘WHEAT’))

289

(<ActionType.END_TURN: ‘END_TURN’>, None)

Observation Space (Raw)#

Feature Name

Description

Number of Features (N=number of players)

Type

BANK_<resource>

Number of cards of that resource in bank

5

Integer

BANK_DEV_CARDS

Number of development cards in bank

1

Integer

EDGE<i>_P<j>_ROAD

Whether edge i is owned by player j

72 * N

Boolean

NODE<i>_P<j>_SETTLEMENT

Whether player j has a city in node i

54 * N

Boolean

NODE<i>_P<j>_CITY

Whether player j has a city in node i

54 * N

Boolean

PORT<i>_IS_<resource>

Whether node i is port of resource (or THREE_TO_ONE).

9 * 6

Boolean

TILE<i>_HAS_ROBBER

Whether robber is on tile i.

19

Boolean

TILE<i>_IS_<resource>

Whether tile i yields resource (or DESERT).

19 * 6

Boolean

TILE<i>_PROBA

Tile i’s probability of being rolled.

19

Float

IS_DISCARDING

Whether current player must discard. For now, there is only 1 discarding action (at random), since otherwise action space would explode in size.

1

Boolean

IS_MOVING_ROBBER

Whether current player must move robber (because played knight or because rolled a 7).

1

Boolean

P<i>_HAS_ROLLED

Whether player i already rolled dice.

N

Boolean

P0_HAS_PLAYED _DEVELOPMENT_CARD _IN_TURN

Whether current player already played a development card

1

Boolean

P0_ACTUAL_VPS

Total Victory Points (including Victory Point Development Cards)

1

Integer

P0_<resource>_IN_HAND

Number of resource cards in hand

5

Integer

P0_<dev-card>_IN_HAND

Number of dev-card cards in hand

5

Integer

P<i>_NUM_DEVS_IN_HAND

Number of hidden development cards player i has

N

Integer

P<i>_NUM_RESOURCES _IN_HAND

Number of hidden resource cards player i has

N

Integer

P<i>_HAS_ARMY

Whether player <i> has Largest Army

N

Boolean

P<i>_HAS_ROAD

Whether player <i> has Longest Road

N

Boolean

P<i>_ROADS_LEFT

Number of roads pieces player i has outside of board (left to build)

N

Integer

P<i>_SETTLEMENTS_LEFT

Number of settlements player i has outside of board (left to build)

N

Integer

P<i>_CITIES_LEFT

Number of cities player i has outside of board (left to build)

N

Integer

P<i>_LONGEST_ROAD _LENGTH

Length of longest road by player i

N

Integer

P<i>_PUBLIC_VPS

Amount of visible victory points for player i (i.e. doesn’t include hidden victory point cards; only army, road and settlements/cities).

N

Integer

P<i>_<dev-card>_PLAYED

Amount of dev-card cards player i has played in game (VICTORY_POINT not included).

4 * N

Integer

194 * N + 226

get_valid_actions()#
Returns

valid actions

Return type

List[int]

reset(seed=None, options=None)#

Resets the environment to an initial internal state, returning an initial observation and info.

This method generates a new starting state often with some randomness to ensure that the agent explores the state space and learns a generalised policy about the environment. This randomness can be controlled with the seed parameter otherwise if the environment already has a random number generator and reset() is called with seed=None, the RNG is not reset.

Therefore, reset() should (in the typical use case) be called with a seed right after initialization and then never again.

For Custom environments, the first line of reset() should be super().reset(seed=seed) which implements the seeding correctly.

Changed in version v0.25: The return_info parameter was removed and now info is expected to be returned.

Parameters
  • seed (optional int) – The seed that is used to initialize the environment’s PRNG (np_random). If the environment does not already have a PRNG and seed=None (the default option) is passed, a seed will be chosen from some source of entropy (e.g. timestamp or /dev/urandom). However, if the environment already has a PRNG and seed=None is passed, the PRNG will not be reset. If you pass an integer, the PRNG will be reset even if it already exists. Usually, you want to pass an integer right after the environment has been initialized and then never again. Please refer to the minimal example above to see this paradigm in action.

  • options (optional dict) – Additional information to specify how the environment is reset (optional, depending on the specific environment)

Returns

Observation of the initial state. This will be an element of observation_space

(typically a numpy array) and is analogous to the observation returned by step().

info (dictionary): This dictionary contains auxiliary information complementing observation. It should be analogous to

the info returned by step().

Return type

observation (ObsType)

step(action)#

Run one timestep of the environment’s dynamics using the agent actions.

When the end of an episode is reached (terminated or truncated), it is necessary to call reset() to reset this environment’s state for the next episode.

Changed in version 0.26: The Step API was changed removing done in favor of terminated and truncated to make it clearer to users when the environment had terminated or truncated which is critical for reinforcement learning bootstrapping algorithms.

Parameters

action (ActType) – an action provided by the agent to update the environment state.

Returns

An element of the environment’s observation_space as the next observation due to the agent actions.

An example is a numpy array containing the positions and velocities of the pole in CartPole.

reward (SupportsFloat): The reward as a result of taking the action. terminated (bool): Whether the agent reaches the terminal state (as defined under the MDP of the task)

which can be positive or negative. An example is reaching the goal state or moving into the lava from the Sutton and Barton, Gridworld. If true, the user needs to call reset().

truncated (bool): Whether the truncation condition outside the scope of the MDP is satisfied.

Typically, this is a timelimit, but could also be used to indicate an agent physically going out of bounds. Can be used to end the episode prematurely before a terminal state is reached. If true, the user needs to call reset().

info (dict): Contains auxiliary diagnostic information (helpful for debugging, learning, and logging).

This might, for instance, contain: metrics that describe the agent’s performance state, variables that are hidden from observations, or individual reward terms that are combined to produce the total reward. In OpenAI Gym <v26, it contains “TimeLimit.truncated” to distinguish truncation and termination, however this is deprecated in favour of returning terminated and truncated variables.

done (bool): (Deprecated) A boolean value for if the episode has ended, in which case further step() calls will

return undefined results. This was removed in OpenAI Gym v26 in favor of terminated and truncated attributes. A done signal may be emitted for different reasons: Maybe the task underlying the environment was solved successfully, a certain timelimit was exceeded, or the physics simulation has entered an invalid state.

Return type

observation (ObsType)

catanatron_gym.envs.catanatron_env.from_action_space(action_int, playable_actions)#

maps action_int to catantron.models.actions.Action

catanatron_gym.envs.catanatron_env.to_action_space(action)#

maps action to space_action equivalent integer

Module contents#