Basics of Reinforcement Learning
0 likes221 views
The document provides an introduction to reinforcement learning, outlining its fundamental concepts such as agents, environments, states, actions, and rewards. It emphasizes that reinforcement learning is distinct from supervised learning in that there is no predefined training data, and the agent learns from experience by maximizing rewards. Additionally, it illustrates the concept through the famous Pavlov experiment, demonstrating how behaviors can be learned through reinforcement.
Basics of Reinforcement Learning
- 1. Basics of Reinforcement Learning Spotle.ai Study Material Spotle.ai/Learn
- 2. Spotle.ai Study Material Spotle.ai/Learn Let’s play chess! I just don’t make any possible move without thinking what my opponent’s move can be to counter my move. I try to consider all possible moves that are safe. And then choose the one that I feel is the best move among all. Machines can learn this way. And this learning is called reinforcement machine learning.
- 3. Spotle.ai Study Material Spotle.ai/Learn What is reinforcement learning? First, a particular situation in which the learning will be applicable. You start at a point, you go through several steps to reach a level. In the process you earn a reward point for every correct step and you lose a reward point for every wrong step. Finally, you choose the path with the highest reward point in that particular situation. Agent Environment State Reward Action
- 4. Spotle.ai Study Material Spotle.ai/Learn Terminologies Agent: The learner and the decision maker. Environment: Where the agent learns and decides what actions to perform. Action: A set of actions which the agent can perform. State: The state of the agent in the environment. Reward: For each action selected by the agent the environment provides a reward. Usually a scalar value. Agent Environment State Reward Action
- 5. In supervised learning the training data has the output, that is, the answer in it. Here the model is trained with the correct answer. But in case of reinforcement learning, there is no answer given. The reinforcement agent decides the action to perform based on the maximum reward it receives. There is no training data in reinforcement learning. The machine learns from its experience. Supervised learning? No Spotle.ai Study Material Spotle.ai/Learn Training data Not available
- 6. Spotle.ai Study Material Spotle.ai/Learn Reinforcing your learning Which one to choose? Give reward to all possible ones step by step Choose the one with the maximum reward.Topic A Topic B Topic C
- 7. Spotle.ai Study Material Spotle.ai/Learn Pavlov Experiment TRIAL 1 In the first trial Pavlov gives meat to his dog and the dog starts salivating.
- 8. Spotle.ai Study Material Spotle.ai/Learn Pavlov Experiment TRIAL 2 In the second trial Pavlov does not give meat to his dog but rings a bell. Without seeing the meat the dog does not start salivating.
- 9. Spotle.ai Study Material Spotle.ai/Learn Pavlov Experiment TRIAL 3 In trial 3 Pavlov rings the bell and gives meat to his dog and seeing meat the dog starts salivating.
- 10. Spotle.ai Study Material Spotle.ai/Learn Pavlov Experiment TRIAL 4 In trial 4 Pavlov rings the bell and at this his dog starts salivating, hoping that meat will follow the ringing of the bell. This is learning by reinforcement. The dog was rewarded with meat after the ringing of the bell.
- 11. Summarizing ❖ The input is an initial stage from which the machine starts learning. ❖ There are more than one possible output in a particular problem. ❖ Each output state is given a reward or punishment. ❖ The output with maximum reward is selected to be performed. ❖ The reinforcement learning process is continuous.