相关论文: ROER: Regularized Optimal Experience Replay

The goal of Unsupervised Reinforcement Learning (URL) is to find a reward-agnostic prior policy on a task domain, such that the sample-efficiency on supervised downstream tasks is improved. Although agents initialized with such a prior…

This paper introduces the QDQN-DPER framework to enhance the efficiency of quantum reinforcement learning (QRL) in solving sequential decision tasks. The framework incorporates prioritized experience replay and asynchronous training into…

Feature attribution has gained prominence as a tool for explaining model decisions, yet evaluating explanation quality remains challenging due to the absence of ground-truth explanations. To circumvent this, explanation-guided input…

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

We introduce a problem-level prioritization framework for RL post-training of large language models. Building on insights from prioritized replay in deep RL, as well as prior observations that rollouts with intermediate success rates tend…

On-policy deep reinforcement learning algorithms have low data utilization and require significant experience for policy improvement. This paper proposes a proximal policy optimization algorithm with prioritized trajectory replay (PTR-PPO)…

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common in realistic tasks to prevent unsafe exploration. To address…

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as…

Hindsight Experience Replay (HER) is one of the efficient algorithm to solve Reinforcement Learning tasks related to sparse rewarded environments.But due to its reduced sample efficiency and slower convergence HER fails to perform…

Many problems, such as online ad display, can be formulated as online bipartite matching. The crucial challenge lies in the nature of sequentially-revealed online item information, based on which we make irreversible matching decisions at…

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Exploration poses a fundamental challenge in Reinforcement Learning (RL) with sparse rewards, limiting an agent's ability to learn optimal decision-making due to a lack of informative feedback signals. Self-Imitation Learning (self-IL) has…

Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising method which enhances the performance through rule-based or…

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior.…

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…

Experience replay (ER) improves the data efficiency of off-policy reinforcement learning (RL) algorithms by allowing an agent to store and reuse its past experiences in a replay buffer. While many techniques have been proposed to enhance ER…

Offline reinforcement learning (RL) can learn effective policies from fixed datasets, but deployment objectives may change after training, and in many applications the trained actor cannot be retrained because of data, cost, or governance…

In reinforcement learning (RL) with experience replay, experiences stored in a replay buffer influence the RL agent's performance. Information about how these experiences influence the agent's performance is valuable for various purposes,…