Related papers: Conservative DDPG -- Pessimistic RL without Ensemb…

Offline reinforcement learning (RL) aims to learn decision policies from a fixed batch of logged transitions, without additional environment interaction. Despite remarkable empirical progress, offline RL remains fragile under distribution…

During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular…

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).…

State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard to transfer their success to industrial control problems,…

Continuous trajectory tracking control of quadrotors is complicated when considering noise from the environment. Due to the difficulty in modeling the environmental dynamics, tracking methodologies based on conventional control theory, such…

Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason…

Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust approach that replaces…

The 3D Bin Packing Problem (3D-BPP) is one of the most demanded yet challenging problems in industry, where an agent must pack variable size items delivered in sequence into a finite bin with the aim to maximize the space utilization. It…

Owing to the openness of wireless channels, wireless communication systems are highly susceptible to malicious jamming. Most existing anti-jamming methods rely on the assumption of accurate sensing and optimize parameters on a single…

We introduce PEPO (Pessimistic Ensemble based Preference Optimization), a single-step Direct Preference Optimization (DPO)-like algorithm to mitigate the well-known over-optimization issue in preference learning without requiring the…

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose…

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, conventional methods based on CTDE can suffer from value underestimation and converge to…

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contaminated by adversarial…

Quantization is a promising method that reduces memory usage and computational intensity of Deep Neural Networks (DNNs), but it often leads to significant output error that hinder model deployment. In this paper, we propose Bias…

How to make imitation learning more general when demonstrations are relatively limited has been a persistent problem in reinforcement learning (RL). Poor demonstrations lead to narrow and biased date distribution, non-Markovian human expert…

Offline reinforcement learning (RL) has increasingly become the focus of the artificial intelligent research due to its wide real-world applications where the collection of data may be difficult, time-consuming, or costly. In this paper, we…