Related papers: Unsupervised Behavioral Compression: Learning Low-…
In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an…
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…
Robot learning in high-dimensional control settings, such as humanoid locomotion, presents persistent challenges for reinforcement learning (RL) algorithms due to unstable dynamics, complex contact interactions, and sensitivity to…
Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…
Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. In this work, we study the inductive bias and…
Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…
As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignment and exploration become more challenging, and the long planning horizon hinders mode discovery…
Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the…
Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely determined by their occupancy measures, we propose modeling…
Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In this paper, we study abstraction in the continuous-control setting, and extend the definition of…
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing…
Parameterized movement primitives have been extensively used for imitation learning of robotic tasks. However, the high-dimensionality of the parameter space hinders the improvement of such primitives in the reinforcement learning (RL)…
Contrastive Reinforcement Learning (CRL) provides a promising framework for extracting useful structured representations from unlabeled interactions. By pulling together state-action pairs and their corresponding future states, while…
Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that…
Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need to balance safety and efficiency. Model Predictive Control (MPC) offers structured constraint handling through…
Empowered by deep neural networks, deep reinforcement learning (DRL) has demonstrated tremendous empirical successes in various domains, including games, health care, and autonomous driving. Despite these advancements, DRL is still…
The stochastic and dynamic nature of renewable energy sources and power electronic devices are creating unique challenges for modern power systems. One such challenge is that the conventional mathematical systems models-based optimal active…
Policy search methods are crucial in reinforcement learning, offering a framework to address continuous state-action and partially observable problems. However, the complexity of exploring vast policy spaces can lead to significant…
Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…
Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been…