Learning from Demonstrations and Human Evaluative Feedbacks: Handling Sparsity and Imperfection Using Inverse Reinforcement Learning Approach

<div>(a) and (b) E-puck robot navigating in two different environments. (c) E-puck external camera perspective used to localize its position.</div>

Journal of Robotics

fig10

Figure 10

Figure 10: Learning from Demonstrations and Human Evaluative Feedbacks: Handling Sparsity and Imperfection Using Inverse Reinforcement Learning Approach 

Figure 10 | Learning from Demonstrations and Human Evaluative Feedbacks: Handling Sparsity and Imperfection Using Inverse Reinforcement Learning Approach 