JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.
Towards Continual Reinforcement Learning: A Review and Perspectives
Sign in to Google
to save your progress.
Learn more
* Indicates required question
StudentID
*
Your answer
The following view on the non-stationarity assumes that the environment is stationary but the agent's perception of the environment changes after each action the agent takes:
Non-stationary function view
Non-deterministic action space view
Partially observable view
Discrete time-dependent state view
Clear selection
Degrees of non-stationarity is defined by how many elements of MDP are non-stationary:
True
False
Clear selection
One of the following methods does not belong to explicit knowledge retention approach to continual RL:
Distillation based
Learning to adapt
Latent parameter storage
Rehearsal based
Clear selection
One of the following approaches to Continual RL targets catastrophic forgetting:
Meta learning
Leveraging shared structure
Explicit knowledge retention
Clear selection
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google.
Report Abuse
-
Terms of Service
-
Privacy Policy
Forms
