Search Results for author:
Found 9 papers, 6 papers with code
Elephant Neural Networks: Born to Be a Continual Learner
We show that by simply replacing classical activation functions with elephant activation functions, we can significantly improve the resilience of neural networks to catastrophic forgetting.
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings.
Learning to Optimize for Reinforcement Learning
Reinforcement learning (RL) is essentially different from supervised learning and in practice these learned optimizers do not work well even in simple RL tasks.
Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation
The experience replay buffer, a standard component in deep reinforcement learning, is often used to reduce forgetting and improve sample efficiency by storing experiences in a large buffer and using them for training later.
Variational Quantum Soft Actor-Critic
In this work, we develop a quantum reinforcement learning algorithm based on soft actor-critic -- one of the state-of-the-art methods for continuous control.
Predictive Representation Learning for Language Modeling
Correlates of secondary information appear in LSTM representations even though they are not part of an \emph{explicitly} supervised prediction task.
Model-free Policy Learning with Reward Gradients
As a key component in reinforcement learning, the reward function is usually devised carefully to guide the agent.
Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Q-learning suffers from overestimation bias, because it approximates the maximum action value using the maximum estimated action value.
Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimation
We learn two groups of latent random variables, where one group corresponds to variables that only cause selection bias, and the other group is relevant for outcome prediction.
