Learn Before
Cumulative Future Reward (Return)
The cumulative future reward, often called the return, represents the total reward an agent accumulates from a specific time step until the final time step . It is a key metric in reinforcement learning for assessing the long-term value of actions or states. The return is calculated by summing the rewards from time step onwards, as shown by the formula: , where represents the reward received at time step .

0
1
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Theory
Concept
Misinformation
Information Overload
Prototypes
General Knowledge References
Information References
Literacy
The Three Forms of Information
Information Disciplines
Information Dissemination
Distributed Summation Implementation
Vector Transformation Formula
Matrix Bracket Notation
Query, Key, and Value in Attention Mechanisms
Cumulative Future Reward (Return)
Causality in Reinforcement Learning
Less Than Inequality
Average Value Notation ()
Function of a Predicted Future Value Notation ()
Draft Model Probability Distribution ()
Weight Matrix Definition ()
Index Calculation for Sequence Start Position
Sequence of Cyclic Subgroups Notation
Greater Than Inequality
Sequence of Predicted Future Values Notation
Conditional Probability of the Next Element in a Sequence
Weighted Softmax Function Notation
Parameterized Prediction Function Notation ()
Data vs. Information in Model Training
Row Vector Notation ()
A climate scientist reads ten peer-reviewed articles, synthesizes the data and arguments presented, and develops a new, deeper understanding of the acceleration of glacial melt. This new understanding within the scientist's mind best exemplifies which of the following?
Start Index Calculation for a Context Window
Vector Prefix Notation
Sequence of Elements in Angle Brackets Notation
A user asks a large language model to explain a scientific concept. The model retrieves relevant data, synthesizes it, and generates a paragraph as a response. The user reads this paragraph and gains a new understanding. Which part of this scenario best exemplifies 'information-as-process'?
Policy in Reinforcement Learning ()
Probability of a Predicted Future Value Notation ()
Predicted Future Value Notation ()
Uncluttered Notation for Encoder-Classifier Models
Data (Information)
Learn After
An agent interacts with an environment over five time steps and receives the following sequence of rewards, starting from time step 1:
[-1, +3, +10, -5, +2]. What is the cumulative future reward (also known as the return) calculated from time step 3?An agent is at time step
t. It must choose between two actions, Action A and Action B. If it chooses Action A, the sequence of rewards it will receive from time steptuntil the end of the episode is[+1, +1, +10]. If it chooses Action B, the sequence of rewards it will receive is[+5, -2, +5]. To maximize its total accumulated reward from this point forward, which action should the agent choose and why?Evaluating Agent Action Sequences