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

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

98
99
100
101
102
103
104
105
106
107
108
109
110
        TaskSpecVRLGLUE3 theTaskSpecObject = new TaskSpecVRLGLUE3();
        theTaskSpecObject.setEpisodic();
        theTaskSpecObject.setDiscountFactor(1.0d);

        //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.");
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
  //or use the official one but just hard code the string instead of constructing it this way.
      TaskSpecVRLGLUE3 theTaskSpecObject = new TaskSpecVRLGLUE3();
        theTaskSpecObject.setEpisodic();
        theTaskSpecObject.setDiscountFactor(1.0d);
  //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);
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
    public void agent_init(String taskSpecification) {
    TaskSpec theTaskSpec=new TaskSpec(taskSpecification);
    System.out.println("Skeleton agent parsed the task spec.");
    System.out.println("Observation have "+theTaskSpec.getNumDiscreteObsDims()+" integer dimensions");
    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
View Full Code Here
74
75
76
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
            double[] obsMins = V3TaskSpec.getObsMins();
            double[] obsMaxs = V3TaskSpec.getObsMaxs();
            for (int i = 0; i < V3TaskSpec.getObsDim(); i++) {
                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)) {
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
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
        if (nextToken.equals("INTS")) {
            //Do the ints
            nextToken = T.nextToken();
            while (nextToken.startsWith("(")) {
                String thisRange = nextToken.substring(1) + " " + T.nextToken(")");
                intObservations.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(")");
                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();
            }
View Full Code Here
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
        assert (theTaskSpec.toTaskSpec().equals(new TaskSpecVRLGLUE3(theTaskSpec.toTaskSpec()).toTaskSpec()));

        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.IntRange

  • 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.