相关论文: Constant in an Ever-Changing World

A reinforcement learning (RL) control policy could fail in a new/perturbed environment that is different from the training environment, due to the presence of dynamic variations. For controlling systems with continuous state and action…

Reinforcement Learning (RL) has shown great potential in complex control tasks, particularly when combined with deep neural networks within the Actor-Critic (AC) framework. However, in practical applications, balancing exploration, learning…

Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications of RL algorithms.…

Sequential recommendation, where user preference is dynamically inferred from sequential historical behaviors, is a critical task in recommender systems (RSs). To further optimize long-term user engagement, offline…

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications. This work…

Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal…

Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into…

Continual learning systems are increasingly deployed in environments where retraining or reset is infeasible, yet many approaches emphasize task performance rather than the evolution of internal representations over time. In this work, we…

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly…

We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors. CIC utilizes contrastive learning between…

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstable. In this work, we show how by simply changing the temporal…

When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as…

We introduce the framework of performative reinforcement learning where the policy chosen by the learner affects the underlying reward and transition dynamics of the environment. Following the recent literature on performative…

Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to…

Robust real-world learning should benefit from both demonstrations and interactions with the environment. Current approaches to learning from demonstration and reward perform supervised learning on expert demonstration data and use…

The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better. In this paper, we propose a…

Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing…