DeepAI AI Chat
Log In Sign Up

Hint assisted reinforcement learning: an application in radio astronomy

by   Sarod Yatawatta, et al.

Model based reinforcement learning has proven to be more sample efficient than model free methods. On the other hand, the construction of a dynamics model in model based reinforcement learning has increased complexity. Data processing tasks in radio astronomy are such situations where the original problem which is being solved by reinforcement learning itself is the creation of a model. Fortunately, many methods based on heuristics or signal processing do exist to perform the same tasks and we can leverage them to propose the best action to take, or in other words, to provide a `hint'. We propose to use `hints' generated by the environment as an aid to the reinforcement learning process mitigating the complexity of model construction. We modify the soft actor critic algorithm to use hints and use the alternating direction method of multipliers algorithm with inequality constraints to train the agent. Results in several environments show that we get the increased sample efficiency by using hints as compared to model free methods.


page 1

page 2

page 3

page 4


Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task

Human-computer interactive systems that rely on machine learning are bec...

Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning

Recent model-free reinforcement learning algorithms have proposed incorp...

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Model-based reinforcement learning algorithms, which aim to learn a mode...

A Quadratic Actor Network for Model-Free Reinforcement Learning

In this work we discuss the incorporation of quadratic neurons into poli...

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

We explored the use of reinforcement learning (RL) agents that can learn...

A Reinforcement Learning Model Using Neural Networks for Music Sight Reading Learning Problem

Music Sight Reading is a complex process in which when it is occurred in...

Accelerating Goal-Directed Reinforcement Learning by Model Characterization

We propose a hybrid approach aimed at improving the sample efficiency in...

Code Repositories


Hint assisted reinforcement learning

view repo