Search Results for author:
Found 15 papers, 1 papers with code
Exploring LLMs as a Source of Targeted Synthetic Textual Data to Minimize High Confidence Misclassifications
Natural Language Processing (NLP) models optimized for predictive performance often make high confidence errors and suffer from vulnerability to adversarial and out-of-distribution data.
When Do Off-Policy and On-Policy Policy Gradient Methods Align?
A well-established off-policy objective is the excursion objective.
Reinforcement Learning by Guided Safe Exploration
Drawing from transfer learning, we also regularize a target policy (the student) towards the guide while the student is unreliable and gradually eliminate the influence of the guide as training progresses.
Diverse Projection Ensembles for Distributional Reinforcement Learning
In contrast to classical reinforcement learning, distributional reinforcement learning algorithms aim to learn the distribution of returns rather than their expected value.
The Role of Diverse Replay for Generalisation in Reinforcement Learning
We motivate mathematically and show empirically that generalisation to tasks that are "reachable'' during training is improved by increasing the diversity of transitions in the replay buffer.
Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
In this paper, we provide a mathematical characterization of this phenomenon, which we refer to as policy confounding, and show, through a series of examples, when and how it occurs in practice.
E-MCTS: Deep Exploration in Model-Based Reinforcement Learning by Planning with Epistemic Uncertainty
One of the most well-studied and highly performing planning approaches used in Model-Based Reinforcement Learning (MBRL) is Monte-Carlo Tree Search (MCTS).
Model-based Reinforcement Learning
reinforcement-learning
+1
Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning.
Abstraction-Refinement for Hierarchical Probabilistic Models
The key ideas to accelerate analysis of such programs are (1) to treat the behavior of the subroutine as uncertain and only remove this uncertainty by a detailed analysis if needed, and (2) to abstract similar subroutines into a parametric template, and then analyse this template.
Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL).
Exploiting Submodular Value Functions For Scaling Up Active Perception
Furthermore, we show that, under certain conditions, including submodularity, the value function computed using greedy PBVI is guaranteed to have bounded error with respect to the optimal value function.
Solving Transition-Independent Multi-agent MDPs with Sparse Interactions (Extended version)
In cooperative multi-agent sequential decision making under uncertainty, agents must coordinate to find an optimal joint policy that maximises joint value.
Influence-Optimistic Local Values for Multiagent Planning --- Extended Version
Recent years have seen the development of methods for multiagent planning under uncertainty that scale to tens or even hundreds of agents.
Incremental Clustering and Expansion for Faster Optimal Planning in Dec-POMDPs
We provide theoretical guarantees that, when a suitable heuristic is used, both incremental clustering and incremental expansion yield algorithms that are both complete and search equivalent.
Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games
Such problems can be modeled as collaborative Bayesian games in which each agent receives private information in the form of its type.
