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
Baseline Method for Policy Gradient Variance Reduction
An agent is being trained in an environment where its sole objective is to maximize the sum of rewards it collects during an episode. The agent completes two separate episodes, receiving the following sequences of rewards:
- Episode A:
[+2, +2, +2, +2, +2] - Episode B:
[-5, -5, +10, +10, +1]
Based on the agent's primary objective, which statement correctly compares the outcomes of these two episodes?
- Episode A:
Robot Navigation Path Selection
Calculating Episode Return
Cumulative Future Reward (Return)
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