Search Results for author:
Found 26 papers, 7 papers with code
Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel
Recent work has shown that training wide neural networks with gradient descent is formally equivalent to computing the mean of the posterior distribution in a Gaussian Process (GP) with the Neural Tangent Kernel (NTK) as the prior covariance and zero aleatoric noise \parencite{jacot2018neural}.
On the Importance of Uncertainty in Decision-Making with Large Language Models
We compare this baseline to LLM bandits that make active use of uncertainty estimation by integrating the uncertainty in a Thompson Sampling policy.
Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
In this paper, we present a reinforcement learning framework that solves for such limitations by directly optimizing for user satisfaction metrics via the use of a simulated playlist-generation environment.
Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay
In this context, we study a content exploration task, which we formalize as a multi-armed bandit problem with delayed rewards.
A Strong Baseline for Batch Imitation Learning
Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making.
Imitation Learning by Reinforcement Learning
Imitation learning algorithms learn a policy from demonstrations of expert behavior.
Information Directed Reward Learning for Reinforcement Learning
For many reinforcement learning (RL) applications, specifying a reward is difficult.
Estimating $α$-Rank by Maximizing Information Gain
We show the benefits of using information gain as compared to the confidence interval criterion of ResponseGraphUCB (Rowland et al. 2019), and provide theoretical results justifying our method.
Regularized Policies are Reward Robust
Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy.
Evaluating the Robustness of Collaborative Agents
We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness.
Deep Interactive Bayesian Reinforcement Learning via Meta-Learning
The optimal adaptive behaviour under uncertainty over the other agents' strategies w. r. t.
DRIFT: Deep Reinforcement Learning for Functional Software Testing
Efficient software testing is essential for productive software development and reliable user experiences.
Discount Factor as a Regularizer in Reinforcement Learning
Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor.
AMRL: Aggregated Memory For Reinforcement Learning
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
Conservative Uncertainty Estimation By Fitting Prior Networks
Obtaining high-quality uncertainty estimates is essential for many applications of deep neural networks.
Better Exploration with Optimistic Actor Critic
To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function.
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
We discuss those differences and propose modifications to existing regularization techniques in order to better adapt them to RL.
Better Exploration with Optimistic Actor-Critic
To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function.
Multi-task Batch Reinforcement Learning with Metric Learning
To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards.
Pre-training as Batch Meta Reinforcement Learning with tiMe
Combining ideas from Batch RL and Meta RL, we propose tiMe, which learns distillation of multiple value functions and MDP embeddings from only existing data.
Fourier Policy Gradients
We propose a new way of deriving policy gradient updates for reinforcement learning.
Expected Policy Gradients for Reinforcement Learning
For Gaussian policies, we introduce an exploration method that uses covariance proportional to the matrix exponential of the scaled Hessian of the critic with respect to the actions.
Expected Policy Gradients
We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning.
Alternating Optimisation and Quadrature for Robust Control
ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy.
Value Iteration with Options and State Aggregation
This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction.
Properties of the Least Squares Temporal Difference learning algorithm
This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumental variables, the linear dynamical system view as well as the limit of the TD iteration.
