2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLSP-27.5
Paper Title POLICY AUGMENTATION: AN EXPLORATION STRATEGY FOR FASTER CONVERGENCE OF DEEP REINFORCEMENT LEARNING ALGORITHMS
Authors Arash Mahyari, Florida Institute For Human and Machine Cognition (IHMC), United States
SessionMLSP-27: Reinforcement Learning 3
LocationGather.Town
Session Time:Thursday, 10 June, 13:00 - 13:45
Presentation Time:Thursday, 10 June, 13:00 - 13:45
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-SLER] Sequential learning; sequential decision methods
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Despite advancements in deep reinforcement learning algorithms, developing an effective exploration strategy is still an open problem. Most existing exploration strategies either are based on simple heuristics, or require the model of the environment, or train additional deep neural networks to generate imagination-augmented paths. In this paper, a revolutionary algorithm, called \textit{Policy Augmentation}, is introduced. \textit{Policy Augmentation} is based on a newly developed inductive matrix completion method. The proposed algorithm augments the values of unexplored state-action pairs, helping the agent take actions that will result in high-value returns while the agent is in the early episodes. Training deep reinforcement learning algorithms with high-value rollouts leads to the faster convergence of deep reinforcement learning algorithms. Our experiments show the superior performance of \textit{Policy Augmentation}. The code can be found at: https://github.com/arashmahyari/PolicyAugmentation.