Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:01,110 --> 00:00:04,770 ہیلو مصنوعی ذہانت کے کورس میں دوبارہ خوش آمدید۔ 2 00:00:04,770 --> 00:00:09,420 Today we're going to discuss the plan of attack for the section we're talking about kill learning. 3 00:00:09,450 --> 00:00:15,000 And we've got quite a few tutorials so I think it is a good idea for us to quickly go through them to 4 00:00:15,000 --> 00:00:20,580 understand what to expect in the upcoming videos. 5 00:00:20,580 --> 00:00:21,650 So here we go. 6 00:00:22,140 --> 00:00:22,560 All right. 7 00:00:22,560 --> 00:00:25,230 What we will learn in this section. 8 00:00:25,230 --> 00:00:31,650 First things first we will talk about what reinforcement learning actually is and what the philosophic 9 00:00:31,690 --> 00:00:37,890 behind reinforcement learning is and how reinforcement learning actually can be seen in real life and 10 00:00:37,890 --> 00:00:44,540 how it relates to things that we observe in real life are actually things that we do ourselves. 11 00:00:44,790 --> 00:00:51,630 They don't talk about the bellmen equation very fundamental concept underpinning everything or a lot 12 00:00:51,630 --> 00:00:56,580 of things that are happening and for reinforcement learning especially in the space of CULE learning 13 00:00:56,940 --> 00:01:01,700 and what we're going to be discussing in this section of the course and in the following sections. 14 00:01:01,800 --> 00:01:09,280 Then we'll talk about the plan and the plan that and raw iron artificial intelligence comes up with 15 00:01:09,300 --> 00:01:15,990 in order to navigate inside environments we'll see what that how that comes together very quick but 16 00:01:15,990 --> 00:01:17,270 quite interesting. 17 00:01:17,720 --> 00:01:22,890 There we'll talk about market of decision processes and your concept we're going to introduce a very 18 00:01:22,890 --> 00:01:31,620 new concept which will slowly even add a layer of sophistication to our Belman equation to our whole 19 00:01:31,800 --> 00:01:37,070 reinforcement learning to our CULE learning concepts and that's the way this section is structured that 20 00:01:37,290 --> 00:01:43,080 we introduce the Bollmann equation a very simplistic form and then slowly throughout the tutorials we 21 00:01:43,260 --> 00:01:48,550 adds layers of sophistication to it in order to get to the final version. 22 00:01:48,690 --> 00:01:53,880 That is our designated destination in terms of Hillary but we'll get there slowly. 23 00:01:54,000 --> 00:01:58,830 In order for us to have enough time to process all that information and let it settle in. 24 00:01:58,890 --> 00:02:05,400 And mark of dissident proses is an extra layer of sophistication on top of what we've discussed or what 25 00:02:05,400 --> 00:02:11,220 we will have or it discussed by then there will talk about policies versus plans. 26 00:02:11,220 --> 00:02:13,830 Another interesting Tauriel they're all interesting. 27 00:02:13,830 --> 00:02:19,590 Just another quick tutorial on how policy is different from plans and what the differences there are 28 00:02:19,590 --> 00:02:25,980 and these are terms that you will probably hear or read in the literature if you're going to be delving 29 00:02:25,980 --> 00:02:29,980 into it to get additional information on reinforcement learning. 30 00:02:29,980 --> 00:02:34,590 They're all talk about adding a living penalty to our environments. 31 00:02:34,770 --> 00:02:41,850 And that's that's kind of another way of adding complexity into the environments that our agents are 32 00:02:41,850 --> 00:02:43,340 going to be operating in. 33 00:02:43,370 --> 00:02:48,780 They're all talk about the intuition behind keep learning so up until that tutorial we're going to be 34 00:02:48,780 --> 00:02:50,690 talking values of states. 35 00:02:50,790 --> 00:02:57,300 And then finally we're going to switch to talking about values or actions or cube values and then we're 36 00:02:57,300 --> 00:02:59,880 going to introduce the temporal difference. 37 00:02:59,910 --> 00:03:06,690 This is a tutorial where everything that we've learned is going to come together to explain how exactly 38 00:03:06,690 --> 00:03:13,930 do agents or artificial does artificial intelligence learn how does it update its values through all 39 00:03:14,090 --> 00:03:16,420 the iterative process that is going through. 40 00:03:16,830 --> 00:03:23,100 And then finally we're going to look at a visible zation of learning so we're going to take everything 41 00:03:23,100 --> 00:03:29,550 we learn and we're going to look at it happen in front of our eyes and watch an artificial intelligence 42 00:03:29,730 --> 00:03:35,870 actually perform CULE learning and do all the things that we're going to discuss on an intuitive level 43 00:03:35,880 --> 00:03:42,600 is going to actually do in practice and that will help us even further grasp that knowledge that we're 44 00:03:42,810 --> 00:03:44,530 going to be coming off in the section. 45 00:03:44,550 --> 00:03:47,460 So hopefully you're very excited about these upcoming tutorials. 46 00:03:47,460 --> 00:03:48,800 I definitely am. 47 00:03:48,810 --> 00:03:55,380 And there some very interesting slides coming up and more important the concepts themselves are very 48 00:03:55,380 --> 00:03:59,540 very interesting and I'm sure you're going to enjoy them quite a lot. 49 00:03:59,760 --> 00:04:01,410 And I look forward to seeing you next time. 50 00:04:01,410 --> 00:04:03,080 Until then enjoy AI. 5965