Search Results for author:
Found 20 papers, 2 papers with code
Provably Sample Efficient RLHF via Active Preference Optimization
Experimental evaluations on a human preference dataset validate \texttt{APO}'s efficacy as a sample-efficient and practical solution to data collection for RLHF, facilitating alignment of LLMs with human preferences in a cost-effective and scalable manner.
On the Safety Concerns of Deploying LLMs/VLMs in Robotics: Highlighting the Risks and Vulnerabilities
However, such integration can introduce significant vulnerabilities, in terms of their susceptibility to adversarial attacks due to the language models, potentially leading to catastrophic consequences.
MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences
Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.
Beyond Text: Improving LLM's Decision Making for Robot Navigation via Vocal Cues
We present "Beyond Text"; an approach that improves LLM decision-making by integrating audio transcription along with a subsection of these features, which focus on the affect and more relevant in human-robot conversations.
REBEL: A Regularization-Based Solution for Reward Overoptimization in Robotic Reinforcement Learning from Human Feedback
Current methods to mitigate this misalignment work by learning reward functions from human preferences; however, they inadvertently introduce a risk of reward overoptimization.
Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey
But in parallel to the development of detection frameworks, researchers have also concentrated on designing strategies to elude detection, i. e., focusing on the impossibilities of AI-generated text detection.
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning
We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning using utility or preference-based feedback.
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
To address these limitations, we introduce a generalized attack framework that has the flexibility to model to what extent the adversary is able to control the agent, and allows the attacker to regulate the state distribution shift and produce stealthier adversarial policies.
On the Possibilities of AI-Generated Text Detection
Our work addresses the critical issue of distinguishing text generated by Large Language Models (LLMs) from human-produced text, a task essential for numerous applications.
RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback
Reinforcement learning-based policies for continuous control robotic navigation tasks often fail to adapt to changes in the environment during real-time deployment, which may result in catastrophic failures.
STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning
Directed Exploration is a crucial challenge in reinforcement learning (RL), especially when rewards are sparse.
Model-based Reinforcement Learning
reinforcement-learning
+1
Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies
In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems.
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the setting when transition model is Gaussian or Lipschitz, and demands a posterior estimate whose representational complexity grows unbounded with time.
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
Doing so incurs a persistent bias that appears in the attenuation rate of the expected policy gradient norm, which is inversely proportional to the radius of the action space.
Transformers at SemEval-2020 Task 11: Propaganda Fragment Detection Using Diversified BERT Architectures Based Ensemble Learning
In this paper, we present our approach for the {'}Detection of Propaganda Techniques in News Articles{'} task as a part of the 2020 edition of International Workshop on Semantic Evaluation.
FairMixRep : Self-supervised Robust Representation Learning for Heterogeneous Data with Fairness constraints
Representation Learning in a heterogeneous space with mixed variables of numerical and categorical types has interesting challenges due to its complex feature manifold.
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.
Learning Representation for Mixed Data Types with a Nonlinear Deep Encoder-Decoder Framework
Representation of data on mixed variables, numerical and categorical types to get suitable feature map is a challenging task as important information lies in a complex non-linear manifold.
Graph Spectral Feature Learning for Mixed Data of Categorical and Numerical Type
In this work, we propose a novel strategy to explicitly model the probabilistic dependence structure among the mixed type of variables by an undirected graph.
