Related papers: Continual Reinforcement Learning with Multi-Timesc…
Multi-Agent Experience Replay (MER) is a key component of off-policy reinforcement learning~(RL) algorithms. By remembering and reusing experiences from the past, experience replay significantly improves the stability of RL algorithms and…
The transformer architecture and variants presented remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the presence of…
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…
Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…
This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain…
Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific…
Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…
Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying…
Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently proposed as a possible…
Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading…
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically…
Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…
One of the key behavioral characteristics used in neuroscience to determine whether the subject of study -- be it a rodent or a human -- exhibits model-based learning is effective adaptation to local changes in the environment, a particular…
Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…
Modern multi-agent reinforcement learning (RL) algorithms hold great potential for solving a variety of real-world problems. However, they do not fully exploit cross-agent knowledge to reduce sample complexity and improve performance.…
Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advances in machine learning involve larger neural networks with…
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a…
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based…