相关论文: Getting By Goal Misgeneralization With a Little He…

Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional…

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized…

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks…

In this paper, we propose Rogue-Gym, a simple and classic style roguelike game built for evaluating generalization in reinforcement learning (RL). Combined with the recent progress of deep neural networks, RL has successfully trained…

This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment. We assume that the…

Inferring other agents' mental states such as their knowledge, beliefs and intentions is thought to be essential for effective interactions with other agents. Recently, multiagent systems trained via deep reinforcement learning have been…

The aim of path planning is to reach the goal from starting point by searching for the route of an agent. In the path planning, the routes may vary depending on the number of variables such that it is important for the agent to reach…

For groups of autonomous agents to achieve a particular goal, they must engage in coordination and long-horizon reasoning. However, designing reward functions to elicit such behavior is challenging. In this paper, we study how…

Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training…

Learning from previously collected datasets of expert data offers the promise of acquiring robotic policies without unsafe and costly online explorations. However, a major challenge is a distributional shift between the states in the…

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or…

Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment in an otherwise fixed enterprise scenario -- and evaluate…

Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading…

There is a growing interest in Multi-Agent Reinforcement Learning (MARL) as the first steps towards building general intelligent agents that learn to make low and high-level decisions in non-stationary complex environments in the presence…

Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate…

As humans and animals learn in the natural world, they encounter distributions of entities, situations and events that are far from uniform. Typically, a relatively small set of experiences are encountered frequently, while many important…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or…