Double sparse deep reinforcement learning via multilayer sparse coding and nonconvex regularized pruning
H Zhao, J Wu, Z Li, W Chen… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Deep reinforcement learning (DRL), which highly depends on the data representation, has
shown its potential in many practical decision-making problems. However, the process of …
shown its potential in many practical decision-making problems. However, the process of …
Learning to stop cut generation for efficient mixed-integer linear programming
Cutting planes (cuts) play an important role in solving mixed-integer linear programs
(MILPs), as they significantly tighten the dual bounds and improve the solving performance …
(MILPs), as they significantly tighten the dual bounds and improve the solving performance …
Accelerate presolve in large-scale linear programming via reinforcement learning
Large-scale LP problems from industry usually contain much redundancy that severely hurts
the efficiency and reliability of solving LPs, making presolve (ie, the problem simplification …
the efficiency and reliability of solving LPs, making presolve (ie, the problem simplification …
Generalization error for portable rewards in transfer imitation learning
The reward transfer paradigm in transfer imitation learning (TIL) leverages the reward
learned via inverse reinforcement learning (IRL) in the source environment to re-optimize a …
learned via inverse reinforcement learning (IRL) in the source environment to re-optimize a …
Dictionary learning-based reinforcement learning with non-convex sparsity regularizer
H Zhao, J Wang, X Huang, Z Li, S Xie - CAAI International Conference on …, 2022 - Springer
Spare representations can help improve value prediction and control performances in
Reinforcement Learning (RL), by capturing most essential features from states and ignoring …
Reinforcement Learning (RL), by capturing most essential features from states and ignoring …