Related papers: Two-Memory Reinforcement Learning
Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term…
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first…
Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the…
Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…
Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn…
Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…
Nowadays, model-free reinforcement learning algorithms have achieved remarkable performance on many decision making and control tasks, but high sample complexity and low sample efficiency still hinder the wide use of model-free…
Inspired by the cognitive science theory, we explicitly model an agent with both semantic and episodic memory systems, and show that it is better than having just one of the two memory systems. In order to show this, we have designed and…
Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem…
Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is efficient and optimal in fully observable environments.…
This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected…
Reinforcement learning has achieved remarkable success in robot learning. However, under challenging exploration and contact-rich dynamics, early-stage training is frequently dominated by premature terminations such as collisions and falls.…
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of parametric machine learning systems is their failure…
We introduce a two-player model of reinforcement learning with memory. Past actions of an iterated game are stored in a memory and used to determine player's next action. To examine the behaviour of the model some approximate methods are…
Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…
The strength of multimodal learning lies in its ability to integrate information from various sources, providing rich and comprehensive insights. However, in real-world scenarios, multi-modal systems often face the challenge of dynamic…
Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…
Traditional memory writing operations proceed one bit at a time, where e.g. an individual magnetic domain is force-flipped by a localized external field. One way to increase material storage capacity would be to write several bits at a time…
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too…
Designing an effective reward function has long been a challenge in reinforcement learning, particularly for complex tasks in unstructured environments. To address this, various learning paradigms have emerged that leverage different forms…