Search Results for author:
Found 11 papers, 6 papers with code
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
In this paper, we establish the global optimality and convergence rate of an off-policy actor critic algorithm in the tabular setting without using density ratio to correct the discrepancy between the state distribution of the behavior policy and that of the target policy.
Reinforcement Learning Framework for Deep Brain Stimulation Study
Malfunctioning neurons in the brain sometimes operate synchronously, reportedly causing many neurological diseases, e. g. Parkinson's.
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
However, recent work has shown limitations of this approach when label distributions differ between the source and target domains.
Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates
To implement the principles prescribed by our theory, we propose an agent, Dr Jekyll & Mr Hyde (JH), with a double personality: Dr Jekyll purely exploits while Mr Hyde purely explores.
Learning Invariances for Policy Generalization
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks.
On the Learning Dynamics of Deep Neural Networks
While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood.
Increasing Robustness to Spurious Correlations using Forgettable Examples
Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks.
Natural Language Inference
Natural Language Understanding
+2
Estimating savings in parking demand using shared vehicles for home-work commuting
The increasing availability and adoption of shared vehicles as an alternative to personally-owned cars presents ample opportunities for achieving more efficient transportation in cities.
Computers and Society Social and Information Networks
Decomposed Mutual Information Estimation for Contrastive Representation Learning
We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views.
On the Convergence of SARSA with Linear Function Approximation
SARSA, a classical on-policy control algorithm for reinforcement learning, is known to chatter when combined with linear function approximation: SARSA does not diverge but oscillates in a bounded region.
Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms
To increase the unlearning speed, we study a novel policy update: the gradient of the cross-entropy loss with respect to the action maximizing $q$, but find that such updates may lead to a decrease in value.
