相关论文: Posterior Coreset Construction with Kernelized Ste…

Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where…

Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predictive models, but often overlook rich local transition geometry…

Deep reinforcement learning (DRL) has shown remarkable success in sequential decision-making problems but suffers from a long training time to obtain such good performance. Many parallel and distributed DRL training approaches have been…

As deep learning models continue to scale, the growing computational demands have amplified the need for effective coreset selection techniques. Coreset selection aims to accelerate training by identifying small, representative subsets of…

Selective experience replay is a popular strategy for integrating lifelong learning with deep reinforcement learning. Selective experience replay aims to recount selected experiences from previous tasks to avoid catastrophic forgetting.…

Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of…

Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value functions and combining…

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally…

We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is…

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

Recent breakthroughs and successful deployment of large language and vision models in a constrained environment predominantly follow a two phase approach. First, large models are trained to achieve peak performance, followed by a model…

We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs). Both the reward functions and the state transition kernels are unknown and allowed to vary…

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…

Traditional model-based reinforcement learning (RL) methods generate forward rollout traces using the learnt dynamics model to reduce interactions with the real environment. The recent model-based RL method considers the way to learn a…

Measure transport underpins several recent algorithms for posterior approximation in the Bayesian context, wherein a transport map is sought to minimise the Kullback--Leibler divergence (KLD) from the posterior to the approximation. The KLD…

Restricted Boltzmann machines (RBMs) are a powerful class of generative models, but their training requires computing a gradient that, unlike supervised backpropagation on typical loss functions, is notoriously difficult even to…

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…

Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender systems, but existing algorithms struggle with the curse of dimensionality in such large discrete action…

Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimization, biology,…