Related papers: SEAR: Sample Efficient Action Chunking Reinforceme…

Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the high dimensionality of joint action spaces and the presence of out-of-distribution joint…

Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a…

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

The proliferation of location-based services has led to massive spatial data generation. Spatial join is a crucial database operation that identifies pairs of objects from two spatial datasets based on spatial relationships. Due to the…

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

Retrieval-Augmented Generation (RAG) systems critically depend on effective document chunking strategies to balance retrieval quality, latency, and operational cost. Traditional chunking approaches, such as fixed-size, rule-based, or fully…

Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more convenient and…

Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…

Modern search engine ranking pipelines are commonly based on large machine-learned ensembles of regression trees. We propose LEAR, a novel - learned - technique aimed to reduce the average number of trees traversed by documents to…

Many reinforcement learning (RL) applications have combinatorial action spaces, where each action is a composition of sub-actions. A standard RL approach ignores this inherent factorization structure, resulting in a potential failure to…

The ability to learn from large batches of autonomously collected data for policy improvement -- a paradigm we refer to as batch online reinforcement learning -- holds the promise of enabling truly scalable robot learning by significantly…

Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there…

Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the…

In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on…

We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

Q-learning is a widely used algorithm in reinforcement learning (RL), but its convergence can be slow, especially when the discount factor is close to one. Successive Over-Relaxation (SOR) Q-learning, which introduces a relaxation factor to…

Detection and localization of actions in videos is an important problem in practice. State-of-the-art video analytics systems are unable to efficiently and effectively answer such action queries because actions often involve a complex…

In this paper, we develop an algorithm called hierarchal online sequential learning algorithm (H-OS-ELM) for single feed feedforward network with features combined from hundreds of midlayers, the algorithm can learn chunk by chunk with…

Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower…