manikandan-n-07 commited on
Commit
864a7e4
·
1 Parent(s): 6f84aaa

Enhance inference script with multi-task aliases

Browse files
Files changed (2) hide show
  1. data/memory.json +603 -220
  2. inference.py +14 -2
data/memory.json CHANGED
@@ -1,224 +1,4 @@
1
  [
2
- {
3
- "task": "drone_env.core.graders:grade_easy",
4
- "steps": [
5
- {
6
- "step": 1,
7
- "x": 5,
8
- "y": 3,
9
- "action": "DOWN",
10
- "reward": -0.05,
11
- "battery": 0.9833
12
- },
13
- {
14
- "step": 2,
15
- "x": 5,
16
- "y": 4,
17
- "action": "DOWN",
18
- "reward": -0.05,
19
- "battery": 0.9667
20
- },
21
- {
22
- "step": 3,
23
- "x": 4,
24
- "y": 4,
25
- "action": "LEFT",
26
- "reward": -0.05,
27
- "battery": 0.95
28
- },
29
- {
30
- "step": 4,
31
- "x": 4,
32
- "y": 5,
33
- "action": "DOWN",
34
- "reward": -0.05,
35
- "battery": 0.9333
36
- },
37
- {
38
- "step": 5,
39
- "x": 3,
40
- "y": 5,
41
- "action": "LEFT",
42
- "reward": -0.1,
43
- "battery": 0.9167
44
- },
45
- {
46
- "step": 6,
47
- "x": 3,
48
- "y": 6,
49
- "action": "DOWN",
50
- "reward": -0.05,
51
- "battery": 0.9
52
- },
53
- {
54
- "step": 7,
55
- "x": 2,
56
- "y": 6,
57
- "action": "LEFT",
58
- "reward": -0.1,
59
- "battery": 0.8833
60
- },
61
- {
62
- "step": 8,
63
- "x": 2,
64
- "y": 7,
65
- "action": "DOWN",
66
- "reward": -0.05,
67
- "battery": 0.8667
68
- },
69
- {
70
- "step": 9,
71
- "x": 1,
72
- "y": 7,
73
- "action": "LEFT",
74
- "reward": 0.95,
75
- "battery": 0.85
76
- }
77
- ],
78
- "grid_meta": {
79
- "width": 10,
80
- "height": 10
81
- },
82
- "delivery_positions": [
83
- [
84
- 1,
85
- 7
86
- ]
87
- ],
88
- "deliveries_done": 1,
89
- "total_reward": 0.45,
90
- "total_steps": 9
91
- },
92
- {
93
- "task": "drone_env.core.graders:grade_easy",
94
- "steps": [
95
- {
96
- "step": 1,
97
- "x": 8,
98
- "y": 6,
99
- "action": "UP",
100
- "reward": -0.05,
101
- "battery": 0.9833
102
- },
103
- {
104
- "step": 2,
105
- "x": 7,
106
- "y": 6,
107
- "action": "LEFT",
108
- "reward": -0.05,
109
- "battery": 0.9667
110
- },
111
- {
112
- "step": 3,
113
- "x": 7,
114
- "y": 5,
115
- "action": "UP",
116
- "reward": -0.1,
117
- "battery": 0.95
118
- },
119
- {
120
- "step": 4,
121
- "x": 6,
122
- "y": 5,
123
- "action": "LEFT",
124
- "reward": -0.05,
125
- "battery": 0.9333
126
- },
127
- {
128
- "step": 5,
129
- "x": 6,
130
- "y": 4,
131
- "action": "UP",
132
- "reward": -0.05,
133
- "battery": 0.9167
134
- },
135
- {
136
- "step": 6,
137
- "x": 5,
138
- "y": 4,
139
- "action": "LEFT",
140
- "reward": -0.05,
141
- "battery": 0.9
142
- },
143
- {
144
- "step": 7,
145
- "x": 5,
146
- "y": 3,
147
- "action": "UP",
148
- "reward": -0.05,
149
- "battery": 0.8833
150
- },
151
- {
152
- "step": 8,
153
- "x": 4,
154
- "y": 3,
155
- "action": "LEFT",
156
- "reward": -0.05,
157
- "battery": 0.8667
158
- },
159
- {
160
- "step": 9,
161
- "x": 4,
162
- "y": 2,
163
- "action": "UP",
164
- "reward": -0.05,
165
- "battery": 0.85
166
- },
167
- {
168
- "step": 10,
169
- "x": 3,
170
- "y": 2,
171
- "action": "LEFT",
172
- "reward": -0.05,
173
- "battery": 0.8333
174
- },
175
- {
176
- "step": 11,
177
- "x": 3,
178
- "y": 1,
179
- "action": "UP",
180
- "reward": -0.05,
181
- "battery": 0.8167
182
- },
183
- {
184
- "step": 12,
185
- "x": 2,
186
- "y": 1,
187
- "action": "LEFT",
188
- "reward": -0.05,
189
- "battery": 0.8
190
- },
191
- {
192
- "step": 13,
193
- "x": 2,
194
- "y": 0,
195
- "action": "UP",
196
- "reward": -0.05,
197
- "battery": 0.7833
198
- },
199
- {
200
- "step": 14,
201
- "x": 1,
202
- "y": 0,
203
- "action": "LEFT",
204
- "reward": 0.95,
205
- "battery": 0.7667
206
- }
207
- ],
208
- "grid_meta": {
209
- "width": 10,
210
- "height": 10
211
- },
212
- "delivery_positions": [
213
- [
214
- 1,
215
- 0
216
- ]
217
- ],
218
- "deliveries_done": 1,
219
- "total_reward": 0.25,
220
- "total_steps": 14
221
- },
222
  {
223
  "task": "drone_env.core.graders:grade_easy",
224
  "steps": [
@@ -17303,5 +17083,608 @@
17303
  "deliveries_done": 1,
17304
  "total_reward": 1.65,
17305
  "total_steps": 7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17306
  }
17307
  ]
 
1
  [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  {
3
  "task": "drone_env.core.graders:grade_easy",
4
  "steps": [
 
17083
  "deliveries_done": 1,
17084
  "total_reward": 1.65,
17085
  "total_steps": 7
17086
+ },
17087
+ {
17088
+ "task": "drone_env.graders.easy:grade_easy",
17089
+ "steps": [
17090
+ {
17091
+ "step": 1,
17092
+ "x": 7,
17093
+ "y": 6,
17094
+ "action": "RIGHT",
17095
+ "reward": 0.1,
17096
+ "battery": 0.9833,
17097
+ "message": "On road \ud83d\udee3\ufe0f"
17098
+ },
17099
+ {
17100
+ "step": 2,
17101
+ "x": 7,
17102
+ "y": 7,
17103
+ "action": "DOWN",
17104
+ "reward": 0.25,
17105
+ "battery": 0.9667,
17106
+ "message": "Hit obstacle! \ud83d\udea7"
17107
+ },
17108
+ {
17109
+ "step": 3,
17110
+ "x": 8,
17111
+ "y": 7,
17112
+ "action": "RIGHT",
17113
+ "reward": 1.05,
17114
+ "battery": 0.95,
17115
+ "message": "\u2705 Delivery 1/1 done!"
17116
+ }
17117
+ ],
17118
+ "grid_meta": {
17119
+ "width": 10,
17120
+ "height": 10
17121
+ },
17122
+ "delivery_positions": [
17123
+ [
17124
+ 8,
17125
+ 7
17126
+ ]
17127
+ ],
17128
+ "deliveries_done": 1,
17129
+ "total_reward": 1.4,
17130
+ "total_steps": 3
17131
+ },
17132
+ {
17133
+ "task": "drone_env.graders.easy:grade_easy",
17134
+ "steps": [
17135
+ {
17136
+ "step": 1,
17137
+ "x": 7,
17138
+ "y": 8,
17139
+ "action": "LEFT",
17140
+ "reward": 0.1,
17141
+ "battery": 0.9833,
17142
+ "message": "On road \ud83d\udee3\ufe0f"
17143
+ },
17144
+ {
17145
+ "step": 2,
17146
+ "x": 6,
17147
+ "y": 8,
17148
+ "action": "LEFT",
17149
+ "reward": 0.1,
17150
+ "battery": 0.9667,
17151
+ "message": "On road \ud83d\udee3\ufe0f"
17152
+ },
17153
+ {
17154
+ "step": 3,
17155
+ "x": 5,
17156
+ "y": 8,
17157
+ "action": "LEFT",
17158
+ "reward": 0.1,
17159
+ "battery": 0.95,
17160
+ "message": "On road \ud83d\udee3\ufe0f"
17161
+ },
17162
+ {
17163
+ "step": 4,
17164
+ "x": 4,
17165
+ "y": 8,
17166
+ "action": "LEFT",
17167
+ "reward": 0.1,
17168
+ "battery": 0.9333,
17169
+ "message": "On road \ud83d\udee3\ufe0f"
17170
+ },
17171
+ {
17172
+ "step": 5,
17173
+ "x": 3,
17174
+ "y": 8,
17175
+ "action": "LEFT",
17176
+ "reward": 0.1,
17177
+ "battery": 0.9167,
17178
+ "message": "On road \ud83d\udee3\ufe0f"
17179
+ },
17180
+ {
17181
+ "step": 6,
17182
+ "x": 2,
17183
+ "y": 8,
17184
+ "action": "LEFT",
17185
+ "reward": 0.1,
17186
+ "battery": 0.9,
17187
+ "message": "On road \ud83d\udee3\ufe0f"
17188
+ },
17189
+ {
17190
+ "step": 7,
17191
+ "x": 1,
17192
+ "y": 8,
17193
+ "action": "LEFT",
17194
+ "reward": 0.1,
17195
+ "battery": 0.8833,
17196
+ "message": "On road \ud83d\udee3\ufe0f"
17197
+ },
17198
+ {
17199
+ "step": 8,
17200
+ "x": 0,
17201
+ "y": 8,
17202
+ "action": "LEFT",
17203
+ "reward": 0.1,
17204
+ "battery": 0.8667,
17205
+ "message": "On road \ud83d\udee3\ufe0f"
17206
+ },
17207
+ {
17208
+ "step": 9,
17209
+ "x": 0,
17210
+ "y": 7,
17211
+ "action": "UP",
17212
+ "reward": 0.1,
17213
+ "battery": 0.85,
17214
+ "message": "On road \ud83d\udee3\ufe0f"
17215
+ },
17216
+ {
17217
+ "step": 10,
17218
+ "x": 1,
17219
+ "y": 7,
17220
+ "action": "RIGHT",
17221
+ "reward": 0.1,
17222
+ "battery": 0.8333,
17223
+ "message": "On road \ud83d\udee3\ufe0f"
17224
+ },
17225
+ {
17226
+ "step": 11,
17227
+ "x": 0,
17228
+ "y": 7,
17229
+ "action": "LEFT",
17230
+ "reward": 0.1,
17231
+ "battery": 0.8167,
17232
+ "message": "On road \ud83d\udee3\ufe0f"
17233
+ },
17234
+ {
17235
+ "step": 12,
17236
+ "x": 0,
17237
+ "y": 7,
17238
+ "action": "LEFT",
17239
+ "reward": 0.2,
17240
+ "battery": 0.8,
17241
+ "message": "Hit LEFT boundary! \ud83d\udeab"
17242
+ },
17243
+ {
17244
+ "step": 13,
17245
+ "x": 0,
17246
+ "y": 6,
17247
+ "action": "UP",
17248
+ "reward": 0.1,
17249
+ "battery": 0.7833,
17250
+ "message": "On road \ud83d\udee3\ufe0f"
17251
+ },
17252
+ {
17253
+ "step": 14,
17254
+ "x": 1,
17255
+ "y": 6,
17256
+ "action": "RIGHT",
17257
+ "reward": 0.1,
17258
+ "battery": 0.7667,
17259
+ "message": "On road \ud83d\udee3\ufe0f"
17260
+ },
17261
+ {
17262
+ "step": 15,
17263
+ "x": 0,
17264
+ "y": 6,
17265
+ "action": "LEFT",
17266
+ "reward": 0.1,
17267
+ "battery": 0.75,
17268
+ "message": "On road \ud83d\udee3\ufe0f"
17269
+ },
17270
+ {
17271
+ "step": 16,
17272
+ "x": 1,
17273
+ "y": 6,
17274
+ "action": "RIGHT",
17275
+ "reward": 0.1,
17276
+ "battery": 0.7333,
17277
+ "message": "On road \ud83d\udee3\ufe0f"
17278
+ },
17279
+ {
17280
+ "step": 17,
17281
+ "x": 0,
17282
+ "y": 6,
17283
+ "action": "LEFT",
17284
+ "reward": 0.1,
17285
+ "battery": 0.7167,
17286
+ "message": "On road \ud83d\udee3\ufe0f"
17287
+ },
17288
+ {
17289
+ "step": 18,
17290
+ "x": 0,
17291
+ "y": 6,
17292
+ "action": "WAIT",
17293
+ "reward": 0.1,
17294
+ "battery": 0.7,
17295
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17296
+ },
17297
+ {
17298
+ "step": 19,
17299
+ "x": 0,
17300
+ "y": 6,
17301
+ "action": "WAIT",
17302
+ "reward": 0.1,
17303
+ "battery": 0.6833,
17304
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17305
+ },
17306
+ {
17307
+ "step": 20,
17308
+ "x": 0,
17309
+ "y": 6,
17310
+ "action": "WAIT",
17311
+ "reward": 0.1,
17312
+ "battery": 0.6667,
17313
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17314
+ },
17315
+ {
17316
+ "step": 21,
17317
+ "x": 0,
17318
+ "y": 6,
17319
+ "action": "WAIT",
17320
+ "reward": 0.1,
17321
+ "battery": 0.65,
17322
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17323
+ },
17324
+ {
17325
+ "step": 22,
17326
+ "x": 0,
17327
+ "y": 6,
17328
+ "action": "WAIT",
17329
+ "reward": 0.1,
17330
+ "battery": 0.6333,
17331
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17332
+ },
17333
+ {
17334
+ "step": 23,
17335
+ "x": 0,
17336
+ "y": 6,
17337
+ "action": "WAIT",
17338
+ "reward": 0.1,
17339
+ "battery": 0.6167,
17340
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17341
+ },
17342
+ {
17343
+ "step": 24,
17344
+ "x": 0,
17345
+ "y": 6,
17346
+ "action": "WAIT",
17347
+ "reward": 0.1,
17348
+ "battery": 0.6,
17349
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17350
+ },
17351
+ {
17352
+ "step": 25,
17353
+ "x": 0,
17354
+ "y": 6,
17355
+ "action": "WAIT",
17356
+ "reward": 0.1,
17357
+ "battery": 0.5833,
17358
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17359
+ },
17360
+ {
17361
+ "step": 26,
17362
+ "x": 0,
17363
+ "y": 6,
17364
+ "action": "WAIT",
17365
+ "reward": 0.1,
17366
+ "battery": 0.5667,
17367
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17368
+ },
17369
+ {
17370
+ "step": 27,
17371
+ "x": 0,
17372
+ "y": 6,
17373
+ "action": "WAIT",
17374
+ "reward": 0.1,
17375
+ "battery": 0.55,
17376
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17377
+ },
17378
+ {
17379
+ "step": 28,
17380
+ "x": 0,
17381
+ "y": 6,
17382
+ "action": "WAIT",
17383
+ "reward": 0.1,
17384
+ "battery": 0.5333,
17385
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17386
+ },
17387
+ {
17388
+ "step": 29,
17389
+ "x": 0,
17390
+ "y": 6,
17391
+ "action": "WAIT",
17392
+ "reward": 0.1,
17393
+ "battery": 0.5167,
17394
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17395
+ },
17396
+ {
17397
+ "step": 30,
17398
+ "x": 0,
17399
+ "y": 6,
17400
+ "action": "WAIT",
17401
+ "reward": 0.1,
17402
+ "battery": 0.5,
17403
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17404
+ },
17405
+ {
17406
+ "step": 31,
17407
+ "x": 0,
17408
+ "y": 6,
17409
+ "action": "WAIT",
17410
+ "reward": 0.1,
17411
+ "battery": 0.4833,
17412
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17413
+ },
17414
+ {
17415
+ "step": 32,
17416
+ "x": 0,
17417
+ "y": 6,
17418
+ "action": "WAIT",
17419
+ "reward": 0.1,
17420
+ "battery": 0.4667,
17421
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17422
+ },
17423
+ {
17424
+ "step": 33,
17425
+ "x": 0,
17426
+ "y": 6,
17427
+ "action": "WAIT",
17428
+ "reward": 0.1,
17429
+ "battery": 0.45,
17430
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17431
+ },
17432
+ {
17433
+ "step": 34,
17434
+ "x": 0,
17435
+ "y": 6,
17436
+ "action": "WAIT",
17437
+ "reward": 0.1,
17438
+ "battery": 0.4333,
17439
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17440
+ },
17441
+ {
17442
+ "step": 35,
17443
+ "x": 0,
17444
+ "y": 6,
17445
+ "action": "WAIT",
17446
+ "reward": 0.1,
17447
+ "battery": 0.4167,
17448
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17449
+ },
17450
+ {
17451
+ "step": 36,
17452
+ "x": 0,
17453
+ "y": 6,
17454
+ "action": "WAIT",
17455
+ "reward": 0.1,
17456
+ "battery": 0.4,
17457
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17458
+ },
17459
+ {
17460
+ "step": 37,
17461
+ "x": 0,
17462
+ "y": 6,
17463
+ "action": "WAIT",
17464
+ "reward": 0.1,
17465
+ "battery": 0.3833,
17466
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17467
+ },
17468
+ {
17469
+ "step": 38,
17470
+ "x": 0,
17471
+ "y": 6,
17472
+ "action": "WAIT",
17473
+ "reward": 0.1,
17474
+ "battery": 0.3667,
17475
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17476
+ },
17477
+ {
17478
+ "step": 39,
17479
+ "x": 0,
17480
+ "y": 6,
17481
+ "action": "WAIT",
17482
+ "reward": 0.1,
17483
+ "battery": 0.35,
17484
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17485
+ },
17486
+ {
17487
+ "step": 40,
17488
+ "x": 0,
17489
+ "y": 6,
17490
+ "action": "WAIT",
17491
+ "reward": 0.1,
17492
+ "battery": 0.3333,
17493
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17494
+ },
17495
+ {
17496
+ "step": 41,
17497
+ "x": 0,
17498
+ "y": 6,
17499
+ "action": "WAIT",
17500
+ "reward": 0.1,
17501
+ "battery": 0.3167,
17502
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17503
+ },
17504
+ {
17505
+ "step": 42,
17506
+ "x": 0,
17507
+ "y": 6,
17508
+ "action": "WAIT",
17509
+ "reward": 0.1,
17510
+ "battery": 0.3,
17511
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17512
+ },
17513
+ {
17514
+ "step": 43,
17515
+ "x": 0,
17516
+ "y": 6,
17517
+ "action": "WAIT",
17518
+ "reward": 0.1,
17519
+ "battery": 0.2833,
17520
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17521
+ },
17522
+ {
17523
+ "step": 44,
17524
+ "x": 0,
17525
+ "y": 6,
17526
+ "action": "WAIT",
17527
+ "reward": 0.1,
17528
+ "battery": 0.2667,
17529
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17530
+ },
17531
+ {
17532
+ "step": 45,
17533
+ "x": 0,
17534
+ "y": 6,
17535
+ "action": "WAIT",
17536
+ "reward": 0.1,
17537
+ "battery": 0.25,
17538
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17539
+ },
17540
+ {
17541
+ "step": 46,
17542
+ "x": 0,
17543
+ "y": 6,
17544
+ "action": "WAIT",
17545
+ "reward": 0.1,
17546
+ "battery": 0.2333,
17547
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17548
+ },
17549
+ {
17550
+ "step": 47,
17551
+ "x": 0,
17552
+ "y": 6,
17553
+ "action": "WAIT",
17554
+ "reward": 0.1,
17555
+ "battery": 0.2167,
17556
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17557
+ },
17558
+ {
17559
+ "step": 48,
17560
+ "x": 0,
17561
+ "y": 6,
17562
+ "action": "WAIT",
17563
+ "reward": 0.1,
17564
+ "battery": 0.2,
17565
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17566
+ },
17567
+ {
17568
+ "step": 49,
17569
+ "x": 0,
17570
+ "y": 6,
17571
+ "action": "WAIT",
17572
+ "reward": 0.1,
17573
+ "battery": 0.1833,
17574
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17575
+ },
17576
+ {
17577
+ "step": 50,
17578
+ "x": 0,
17579
+ "y": 6,
17580
+ "action": "WAIT",
17581
+ "reward": 0.1,
17582
+ "battery": 0.1667,
17583
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17584
+ },
17585
+ {
17586
+ "step": 51,
17587
+ "x": 0,
17588
+ "y": 6,
17589
+ "action": "WAIT",
17590
+ "reward": 0.1,
17591
+ "battery": 0.15,
17592
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17593
+ },
17594
+ {
17595
+ "step": 52,
17596
+ "x": 0,
17597
+ "y": 6,
17598
+ "action": "WAIT",
17599
+ "reward": 0.1,
17600
+ "battery": 0.1333,
17601
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17602
+ },
17603
+ {
17604
+ "step": 53,
17605
+ "x": 0,
17606
+ "y": 6,
17607
+ "action": "WAIT",
17608
+ "reward": 0.1,
17609
+ "battery": 0.1167,
17610
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17611
+ },
17612
+ {
17613
+ "step": 54,
17614
+ "x": 0,
17615
+ "y": 6,
17616
+ "action": "WAIT",
17617
+ "reward": 0.1,
17618
+ "battery": 0.1,
17619
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17620
+ },
17621
+ {
17622
+ "step": 55,
17623
+ "x": 0,
17624
+ "y": 6,
17625
+ "action": "WAIT",
17626
+ "reward": 0.1,
17627
+ "battery": 0.0833,
17628
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17629
+ },
17630
+ {
17631
+ "step": 56,
17632
+ "x": 0,
17633
+ "y": 6,
17634
+ "action": "WAIT",
17635
+ "reward": 0.1,
17636
+ "battery": 0.0667,
17637
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17638
+ },
17639
+ {
17640
+ "step": 57,
17641
+ "x": 0,
17642
+ "y": 6,
17643
+ "action": "WAIT",
17644
+ "reward": 0.1,
17645
+ "battery": 0.05,
17646
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17647
+ },
17648
+ {
17649
+ "step": 58,
17650
+ "x": 0,
17651
+ "y": 6,
17652
+ "action": "WAIT",
17653
+ "reward": 0.1,
17654
+ "battery": 0.0333,
17655
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17656
+ },
17657
+ {
17658
+ "step": 59,
17659
+ "x": 0,
17660
+ "y": 6,
17661
+ "action": "WAIT",
17662
+ "reward": 0.1,
17663
+ "battery": 0.0167,
17664
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17665
+ },
17666
+ {
17667
+ "step": 60,
17668
+ "x": 0,
17669
+ "y": 6,
17670
+ "action": "WAIT",
17671
+ "reward": 0.1,
17672
+ "battery": 0.0,
17673
+ "message": "Drone is idling (WAIT)... \ud83d\udd0b"
17674
+ }
17675
+ ],
17676
+ "grid_meta": {
17677
+ "width": 10,
17678
+ "height": 10
17679
+ },
17680
+ "delivery_positions": [
17681
+ [
17682
+ 2,
17683
+ 3
17684
+ ]
17685
+ ],
17686
+ "deliveries_done": 0,
17687
+ "total_reward": 6.2,
17688
+ "total_steps": 60
17689
  }
17690
  ]
inference.py CHANGED
@@ -44,10 +44,22 @@ API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY") or os.getenv("OPENAI_API
44
  API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
45
  MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-7B-Instruct"
46
 
47
- TASK_NAME = os.getenv("TASK_NAME", "drone_env.graders.easy:grade_easy")
 
 
 
 
 
 
 
 
 
 
 
 
48
  BENCHMARK = os.getenv("DRONE_BENCHMARK", "drone_env_v1")
49
 
50
- MAX_STEPS = 60
51
  TEMPERATURE = 0.0
52
  MAX_TOKENS = 50
53
  SUCCESS_SCORE_THRESHOLD = 0.5
 
44
  API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
45
  MODEL_NAME = os.getenv("MODEL_NAME") or "Qwen/Qwen2.5-7B-Instruct"
46
 
47
+ TASK_MAP = {
48
+ "easy": "drone_env.graders.easy:grade_easy",
49
+ "medium": "drone_env.graders.medium:grade_medium",
50
+ "hard": "drone_env.graders.hard:grade_hard",
51
+ "easy_delivery": "drone_env.graders.easy:grade_easy",
52
+ "medium_delivery": "drone_env.graders.medium:grade_medium",
53
+ "hard_delivery": "drone_env.graders.hard:grade_hard",
54
+ }
55
+
56
+ # Accepts "easy", "medium", "hard" or the full grader path
57
+ RAW_TASK = os.getenv("TASK_NAME", "easy")
58
+ TASK_NAME = TASK_MAP.get(RAW_TASK, RAW_TASK)
59
+
60
  BENCHMARK = os.getenv("DRONE_BENCHMARK", "drone_env_v1")
61
 
62
+ MAX_STEPS = 60 # Default fallback
63
  TEMPERATURE = 0.0
64
  MAX_TOKENS = 50
65
  SUCCESS_SCORE_THRESHOLD = 0.5