Related papers: Successor Features for Transfer in Alternating Mar…

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end…

Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions…

While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a…

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications…

Transactions are an important aspect of human social life, and represent dynamic flow of information, intangible values, such as trust, as well as monetary and social capital. Although much research has been conducted on the nature of…

We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic…

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through…

The widespread deployment of Machine Learning systems everywhere raises challenges, such as dealing with interactions or competition between multiple learners. In that goal, we study multi-agent sequential decision-making by considering…

The Option Keyboard (OK) was recently proposed as a method for transferring behavioral knowledge across tasks. OK transfers knowledge by adaptively combining subsets of known behaviors using Successor Features (SFs) and Generalized Policy…

Transfers play a pivotal role in shaping a football club's success, yet forecasting whether a transfer will succeed remains difficult due to the strong context-dependence of on-field performance. Existing evaluation practices often rely on…

Transfer in Reinforcement Learning aims to improve learning performance on target tasks using knowledge from experienced source tasks. Successor Representations (SR) and their extension Successor Features (SF) are prominent transfer…

In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set…

Game theory serves as a powerful tool for distributed optimization in multi-agent systems in different applications. In this paper we consider multi-agent systems that can be modeled by means of potential games whose potential function…

Multi-agent reinforcement learning is an area of rapid advancement in artificial intelligence and machine learning. One of the important questions to be answered is how to conduct credit assignment in a multi-agent system. There have been…

We present a simple game which mimics the complex dynamics found in most natural and social systems. Intelligent players modify their strategies periodically, depending on their performances. We propose that the agents use hybridized…

Optimal policies in standard MDPs can be obtained using either value iteration or policy iteration. However, in the case of zero-sum Markov games, there is no efficient policy iteration algorithm; e.g., it has been shown that one has to…

Reinforcement learning agents have been mostly developed and evaluated under the assumption that they will operate in a fully autonomous manner -- they will take all actions. In this work, our goal is to develop algorithms that, by learning…

As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…

Humans and animals show remarkable flexibility in adjusting their behaviour when their goals, or rewards in the environment change. While such flexibility is a hallmark of intelligent behaviour, these multi-task scenarios remain an…

Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source…