Reinforcement Learning with Subspaces using Free Energy Paradigm

no code implementations • 13 Dec 2020 • Milad Ghorbani, Reshad Hosseini, Seyed Pooya Shariatpanahi, Majid Nili Ahmadabadi

We propose a free-energy minimization framework for selecting the subspaces and integrate the policy of the state-space into the subspaces.

reinforcement-learning Reinforcement Learning (RL) +1

Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs

no code implementations • 11 Mar 2019 • Saeed Masoudnia, Omid Mersa, Babak N. Araabi, Abdol-Hossein Vahabie, Mohammad Amin Sadeghi, Majid Nili Ahmadabadi

We conducted two sets of experiments based on two different protocols of OSV, i. e., writer-dependent and writer-independent on three signature datasets: GPDS-Synthetic, MCYT, and UT-SIG.

Exploiting generalization in the subspaces for faster model-based learning

no code implementations • 22 Oct 2017 • Maryam Hashemzadeh, Reshad Hosseini, Majid Nili Ahmadabadi

Generalization and faster learning in a subspace are due to many-to-one mapping of experiences from the full-space to each state in the subspace.

Decision Making Reinforcement Learning (RL)

Incremental learning of high-level concepts by imitation

no code implementations • 14 Apr 2017 • Mina Alibeigi, Majid Nili Ahmadabadi, Babak Nadjar Araabi

In ILoCI, observed multimodal spatio-temporal demonstrations are incrementally abstracted and generalized based on both their perceptual and functional similarities during the imitation.

Incremental Learning Vocal Bursts Intensity Prediction