Related papers: Advances in Experience Replay

Learning agents can make use of Reinforcement Learning (RL) to decide their actions by using a reward function. However, the learning process is greatly influenced by the elect of values of the hyperparameters used in the learning…

Continual learning is the one of the most essential abilities for autonomous agents, which can incrementally learn daily-life skills. For this ultimate goal, a simple but powerful method, dark experience replay (DER), has been proposed…

Model-based reinforcement learning is a promising learning strategy for practical robotic applications due to its improved data-efficiency versus model-free counterparts. However, current state-of-the-art model-based methods rely on shaped…

Our work is a simple extension of the paper "Exploration by Random Network Distillation". More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay in order to achieve more efficient and robust exploration…

In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such…

In the training process of Deep Reinforcement Learning (DRL), agents require repetitive interactions with the environment. With an increase in training volume and model complexity, it is still a challenging problem to enhance data…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

Emotional support conversations require more than fluent responses. Supporters need to understand the seeker's situation and emotions, adopt an appropriate strategy, and respond in a natural, human-like manner. Despite advances in large…

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization…

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm.…

Sparse rewards present a difficult problem in reinforcement learning and may be inevitable in certain domains with complex dynamics such as real-world robotics. Hindsight Experience Replay (HER) is a recent replay memory development that…

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses…

We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that…

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories with achieved…

Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data collected in previous iterations to accelerate policy optimization. Classical experience replay treats all past observations uniformly…

An important component of many Deep Reinforcement Learning algorithms is the Experience Replay which serves as a storage mechanism or memory of made experiences. These experiences are used for training and help the agent to stably find the…