Scribd Logo
Upload

Welcome to Scribd!

  • 13 views

    Algorithms For IRL

    Uploaded by

    Chaudhary AArishi Orra
    The document contains 6 figures showing the results of a reinforcement learning experiment. Figure 1 shows the trajectory of a car over 5 time steps. Figures 2-4 show the fitted reward function and how it changes over the car's position. Figures 5 and 6 show how the fraction of state-action disagreements and value of the policy changes over iterations of the algorithm.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Algorithms For IRL

    Uploaded by

    Chaudhary AArishi Orra
    13 views8 pages
    The document contains 6 figures showing the results of a reinforcement learning experiment. Figure 1 shows the trajectory of a car over 5 time steps. Figures 2-4 show the fitted reward function and how it changes over the car's position. Figures 5 and 6 show how the fraction of state-action disagreements and value of the policy changes over iterations of the algorithm.

    Original Title

    Algorithms for IRL

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document contains 6 figures showing the results of a reinforcement learning experiment. Figure 1 shows the trajectory of a car over 5 time steps. Figures 2-4 show the fitted reward function and how it changes over the car's position. Figures 5 and 6 show how the fraction of state-action disagreements and value of the policy changes over iterations of the algorithm.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    13 views8 pages

    Algorithms For IRL

    Uploaded by

    Chaudhary AArishi Orra
    The document contains 6 figures showing the results of a reinforcement learning experiment. Figure 1 shows the trajectory of a car over 5 time steps. Figures 2-4 show the fitted reward function and how it changes over the car's position. Figures 5 and 6 show how the fraction of state-action disagreements and value of the policy changes over iterations of the algorithm.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 8

    1

    0.5

    −0.5

    −1

    −1.5
    1

    2 5

    3 4
    3
    4
    2
    5 1

    1.2

    0.8
    1
    0.6

    0.8 0.4

    0.2
    0.6
    0
    0.4
    −0.2
    1
    0.2 2 5

    3 4
    0 3
    1 4
    2
    2 5 5 1

    3 4
    3
    4
    2
    5 1
    −2.5063

    −2.5063

    −2.5064

    −2.5064

    Fitted Reward
    Goal
    −2.5065

    −2.5065

    −2.5065

    −2.5066

    −2.5067
    −1.2 −1 −0.8 −0.6 −0.4 −0.2 0 0.2 0.4 0.6
    car’s x−position
    3

    Fitted Reward
    0

    −1

    −2

    −3
    −1.2 −1 −0.8 −0.6 −0.4 −0.2 0 0.2 0.4 0.6
    car’s x−position
    0.8

    Fraction of states on which actions disagree


    0.7

    0.6

    0.5

    0.4

    0.3

    0.2

    0.1

    0
    0 5 10 15 20 25
    Iteration number
    7

    5
    Value of policy

    0
    0 5 10 15 20 25
    Iteration number

    You might also like