Related papers: State Space Closure: Revisiting Endless Online Lev…
Continuous-time generative models for crystalline materials enable inverse materials design by learning to predict stable crystal structures, but incorporating explicit target properties into the generative process remains challenging.…
Constrained Reinforcement Learning (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated as…
Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation. This direction is…
Reinforcement learning (RL) in the context of control systems offers wide possibilities of controller adaptation. Given an infinite-horizon cost function, the so-called critic of RL approximates it with a neural net and sends this…
Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating…
Hierarchical reinforcement learning (HRL) effectively improves agents' exploration efficiency on tasks with sparse reward, with the guide of high-quality hierarchical structures (e.g., subgoals or options). However, how to automatically…
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…
Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has…
We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…
State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization…
Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value…
The procedural generation of levels and content in video games is a challenging AI problem. Often such generation relies on an intelligent way of evaluating the content being generated so that constraints are satisfied and/or objectives…
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as…
One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration,…
Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…
Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…
Online recommendation requires handling rapidly changing user preferences. Deep reinforcement learning (DRL) is gaining interest as an effective means of capturing users' dynamic interest during interactions with recommender systems.…
As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…
Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and,…
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction…