Meta-tuning loss functions and data augmentation for few-shot object detection
Few-shot object detection, the problem of modelling novel object detection categories with
few training instances, is an emerging topic in the area of few-shot learning and object …
few training instances, is an emerging topic in the area of few-shot learning and object …
Importance sampling techniques for policy optimization
How can we effectively exploit the collected samples when solving a continuous control task
with Reinforcement Learning? Recent results have empirically demonstrated that multiple …
with Reinforcement Learning? Recent results have empirically demonstrated that multiple …
On the hidden biases of policy mirror ascent in continuous action spaces
We focus on parameterized policy search for reinforcement learning over continuous action
spaces. Typically, one assumes the score function associated with a policy is bounded …
spaces. Typically, one assumes the score function associated with a policy is bounded …
Alleviating parameter-tuning burden in reinforcement learning for large-scale process control
L Zhu, G Takami, M Kawahara, H Kanokogi… - Computers & Chemical …, 2022 - Elsevier
Modern process controllers necessitate high quality models and remedial system re-
identification upon performance degradation. Reinforcement Learning (RL) can be a …
identification upon performance degradation. Reinforcement Learning (RL) can be a …
Truncating trajectories in Monte Carlo reinforcement learning
Abstract In Reinforcement Learning (RL), an agent acts in an unknown environment to
maximize the expected cumulative discounted sum of an external reward signal, ie, the …
maximize the expected cumulative discounted sum of an external reward signal, ie, the …
Smoothing policies and safe policy gradients
Policy gradient (PG) algorithms are among the best candidates for the much-anticipated
applications of reinforcement learning to real-world control tasks, such as robotics. However …
applications of reinforcement learning to real-world control tasks, such as robotics. However …
On the sample complexity and metastability of heavy-tailed policy search in continuous control
Reinforcement learning is a framework for interactive decision-making with incentives
sequentially revealed across time without a system dynamics model. Due to its scaling to …
sequentially revealed across time without a system dynamics model. Due to its scaling to …
MAD for robust reinforcement learning in machine translation
We introduce a new distributed policy gradient algorithm and show that it outperforms
existing reward-aware training procedures such as REINFORCE, minimum risk training …
existing reward-aware training procedures such as REINFORCE, minimum risk training …
Policy gradient algorithms implicitly optimize by continuation
Direct policy optimization in reinforcement learning is usually solved with policy-gradient
algorithms, which optimize policy parameters via stochastic gradient ascent. This paper …
algorithms, which optimize policy parameters via stochastic gradient ascent. This paper …
Adaptive exploration policy for exploration–exploitation tradeoff in continuous action control optimization
M Li, T Huang, W Zhu - International Journal of Machine Learning and …, 2021 - Springer
The optimization of continuous action control is an important research field. It aims to find
optimal decisions by the experience of making decisions in a continuous action control task …
optimal decisions by the experience of making decisions in a continuous action control task …