Search Results for author: Zhikang T. Wang

Found 4 papers, 3 papers with code

Convergent and Efficient Deep Q Learning Algorithm

no code implementations • ICLR 2022 • Zhikang T. Wang, Masahito Ueda

Despite the empirical success of the deep Q network (DQN) reinforcement learning algorithm and its variants, DQN is still not well understood and it does not guarantee convergence.

Q-Learning reinforcement-learning +1

Paper
Add Code

Convergent and Efficient Deep Q Network Algorithm

1 code implementation • 29 Jun 2021 • Zhikang T. Wang, Masahito Ueda

Despite the empirical success of the deep Q network (DQN) reinforcement learning algorithm and its variants, DQN is still not well understood and it does not guarantee convergence.

reinforcement-learning Reinforcement Learning (RL)

Paper
Code

LaProp: Separating Momentum and Adaptivity in Adam

1 code implementation • 12 Feb 2020 • Liu Ziyin, Zhikang T. Wang, Masahito Ueda

We also bound the regret of Laprop on a convex problem and show that our bound differs from that of Adam by a key factor, which demonstrates its advantage.

Style Transfer

Paper
Code

Deep Reinforcement Learning Control of Quantum Cartpoles

1 code implementation • 21 Oct 2019 • Zhikang T. Wang, Yuto Ashida, Masahito Ueda

We generalize a standard benchmark of reinforcement learning, the classical cartpole balancing problem, to the quantum regime by stabilizing a particle in an unstable potential through measurement and feedback.

reinforcement-learning Reinforcement Learning (RL)

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.