Package org.rlcommunity.rlglue.codec.taskspec.ranges

Examples of org.rlcommunity.rlglue.codec.taskspec.ranges.DoubleRange

102
103
104
105
106
107
108
109
110
111
112
        //Specify that there will be an integer observation [0,107] for the state
        theTaskSpecObject.addDiscreteObservation(new IntRange(0, theWorld.getNumStates() - 1));
        //Specify that there will be an integer action [0,3]
        theTaskSpecObject.addDiscreteAction(new IntRange(0, 3));
        //Specify the reward range [-100,10]
        theTaskSpecObject.setRewardRange(new DoubleRange(-100.0d, 10.0d));

        theTaskSpecObject.setExtra("SampleMinesEnvironment(Java) by Brian Tanner.");

        String taskSpecString = theTaskSpecObject.toTaskSpec();
        TaskSpec.checkTaskSpec(taskSpecString);
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
  //Specify that there will be an integer observation [0,20] for the state
        theTaskSpecObject.addDiscreteObservation(new IntRange(0, 20));
  //Specify that there will be an integer action [0,1]
        theTaskSpecObject.addDiscreteAction(new IntRange(0, 1));
  //Specify the reward range [-1,1]
        theTaskSpecObject.setRewardRange(new DoubleRange(-1, 1));

        String taskSpecString = theTaskSpecObject.toTaskSpec();
        TaskSpec.checkTaskSpec(taskSpecString);

    //This actual string this makes is:
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
    System.out.println("Actions have "+theTaskSpec.getNumDiscreteActionDims()+" integer dimensions");
    IntRange theObsRange=theTaskSpec.getDiscreteObservationRange(0);
    System.out.println("Observation (state) range is: "+theObsRange.getMin()+" to "+theObsRange.getMax());
    IntRange theActRange=theTaskSpec.getDiscreteActionRange(0);
    System.out.println("Action range is: "+theActRange.getMin()+" to "+theActRange.getMax());
    DoubleRange theRewardRange=theTaskSpec.getRewardRange();
    System.out.println("Reward range is: "+theRewardRange.getMin()+" to "+theRewardRange.getMax());
   
    //In more complex agents, you would also check for continuous observations and actions, discount factors, etc.
    //Also, these ranges can have special values like "NEGINF, POSINF, UNSPEC (unspecified)".  There is no guarantee
    //that they are all specified and that they are all nice numbers.
    }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
                AbstractRange newRange = null;
                if (obsTypes[i] == 'i') {
                    newRange = new IntRange((int) obsMins[i], (int) obsMaxs[i]);
                }
                if (obsTypes[i] == 'f') {
                    newRange = new DoubleRange(obsMins[i], obsMaxs[i]);
                }
                if (V3TaskSpec.isObsMinNegInfinity(i)) {
                    newRange.setMinNegInf();
                }
                if (V3TaskSpec.isObsMinUnknown(i)) {
                    newRange.setMinUnspecified();
                }
                if (V3TaskSpec.isObsMaxPosInfinity(i)) {
                    newRange.setMaxInf();
                }
                if (V3TaskSpec.isObsMaxUnknown(i)) {
                    newRange.setMaxUnspecified();
                }
                if (obsTypes[i] == 'i') {
                    intObservations.add((IntRange) newRange);
                }
                if (obsTypes[i] == 'f') {
                    doubleObservations.add((DoubleRange) newRange);
                }
            }
        }
        {
            char[] actTypes = V3TaskSpec.getActionTypes();
            double[] actMins = V3TaskSpec.getActionMins();
            double[] actMaxs = V3TaskSpec.getActionMaxs();
            for (int i = 0; i < V3TaskSpec.getActionDim(); i++) {
                AbstractRange newRange = null;
                if (actTypes[i] == 'i') {
                    newRange = new IntRange((int) actMins[i], (int) actMaxs[i]);
                }
                if (actTypes[i] == 'f') {
                    newRange = new DoubleRange(actMins[i], actMaxs[i]);
                }
                if (V3TaskSpec.isActionMinNegInfinity(i)) {
                    newRange.setMinNegInf();
                }
                if (V3TaskSpec.isActionMinUnknown(i)) {
                    newRange.setMinUnspecified();
                }
                if (V3TaskSpec.isActionMaxPosInfinity(i)) {
                    newRange.setMaxInf();
                }
                if (V3TaskSpec.isActionMaxUnknown(i)) {
                    newRange.setMaxUnspecified();
                }
                if (actTypes[i] == 'i') {
                    intActions.add((IntRange) newRange);
                }
                if (actTypes[i] == 'f') {
                    doubleActions.add((DoubleRange) newRange);
                }
            }
        }
        rewardRange = new DoubleRange(V3TaskSpec.getRewardMin(), V3TaskSpec.getRewardMax());
        if (V3TaskSpec.isMinRewardNegInf()) {
            rewardRange.setMinNegInf();
        }
        if (V3TaskSpec.isMinRewardUnknown()) {
            rewardRange.setMinUnspecified();
View Full Code Here
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
        if (nextToken.equals("DOUBLES")) {
            //Do the doubles
            nextToken = T.nextToken();
            while (nextToken.startsWith("(")) {
                String thisRange = nextToken.substring(1) + " " + T.nextToken(")");
                doubleObservations.add(new DoubleRange(thisRange));

                //Advance past the space after the range
                T.nextToken(" ");
                nextToken = T.nextToken();
            }
        }
        if (nextToken.equals("CHARCOUNT")) {
            String numCharToken = T.nextToken();
            numObsChars = Integer.parseInt(numCharToken);
            nextToken = T.nextToken();

        }

        checkLabel("ACTIONS", nextToken);
        nextToken = T.nextToken();
        if (nextToken.equals("INTS")) {
            //Do the ints
            nextToken = T.nextToken();
            while (nextToken.startsWith("(")) {
                String thisRange = nextToken.substring(1) + " " + T.nextToken(")");
                intActions.add(new IntRange(thisRange));

                //Advance past the space after the range
                T.nextToken(" ");
                nextToken = T.nextToken();
            }
        }
        if (nextToken.equals("DOUBLES")) {
            //Do the doubles
            nextToken = T.nextToken();
            while (nextToken.startsWith("(")) {
                String thisRange = nextToken.substring(1) + " " + T.nextToken(")");
                doubleActions.add(new DoubleRange(thisRange));

                //Advance past the space after the range
                T.nextToken(" ");
                nextToken = T.nextToken();
            }
        }
        if (nextToken.equals("CHARCOUNT")) {
            String numCharToken = T.nextToken();
            numActChars = Integer.parseInt(numCharToken);
            nextToken = T.nextToken();

        }



        checkLabel("REWARDS", nextToken);
        nextToken = T.nextToken();
        if (nextToken.startsWith("(")) {
            String rewardRangeString = nextToken.substring(1) + " " + T.nextToken(")");
            rewardRange = new DoubleRange(rewardRangeString);
            T.nextToken(" ");
            nextToken = T.nextToken();

        }
View Full Code Here
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
        TaskSpecVRLGLUE3 sampleTSO = new TaskSpecVRLGLUE3();
        sampleTSO.setEpisodic();
        sampleTSO.setDiscountFactor(0);
        sampleTSO.addDiscreteObservation(new IntRange(0, 1, 3));
        sampleTSO.addContinuousObservation(new DoubleRange(-1.2, .5, 2));
        sampleTSO.addContinuousObservation(new DoubleRange(-.07, .07));
        sampleTSO.setObservationCharLimit(1024);
        sampleTSO.addDiscreteAction(new IntRange(0, 4));
        sampleTSO.setRewardRange(new DoubleRange(-5, 5));
        sampleTSO.setExtra("some other stuff goes here");
        System.out.println(sampleTSO.toTaskSpec());
        assert (sampleTSO.toTaskSpec().equals(new TaskSpecVRLGLUE3(sampleTSO.toTaskSpec()).toTaskSpec()));
        assert (theTaskSpec.toTaskSpec().equals(sampleTSO.toTaskSpec()));
    }
View Full Code Here
TOP

Related Classes of org.rlcommunity.rlglue.codec.taskspec.ranges.DoubleRange

  • org.rlcommunity.rlglue.codec.taskspec.TaskSpecVRLGLUE3
  • SampleMinesEnvironment
  • SkeletonAgent
  • SkeletonEnvironment
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.