Related papers: Prioritized Generative Replay
A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…
We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training. The intuition behind this is that even a…
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…
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.…
In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more…
Deep reinforcement learning has emerged as a powerful tool for a variety of learning tasks, however deep nets typically exhibit forgetting when learning multiple tasks in sequence. To mitigate forgetting, we propose an experience replay…
Reinforcement Learning (RL) has achieved significant success in application domains such as robotics, games and health care. However, training RL agents is very time consuming. Current implementations exhibit poor performance due to…
Prioritized experience replay, which improves sample efficiency by selecting relevant transitions to update parameter estimates, is a crucial component of contemporary value-based deep reinforcement learning models. Typically, transitions…
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,…
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…
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,…
Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…
A central component of training in Reinforcement Learning (RL) is Experience: the data used for training. The mechanisms used to generate and consume this data have an important effect on the performance of RL algorithms. In this paper, we…
We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…
Efficient utilization of the replay buffer plays a significant role in the off-policy actor-critic reinforcement learning (RL) algorithms used for model-free control policy synthesis for complex dynamical systems. We propose a method for…
Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay…
Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal oracle evaluations (computational prediction or wet-lab experiment).…
Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…
A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error.…
Online reinforcement learning (RL) excels in complex, safety-critical domains but suffers from sample inefficiency, training instability, and limited interpretability. Data attribution provides a principled way to trace model behavior back…