Making Universal Policies Universal

• URL: http://arxiv.org/abs/2502.14777v1
• Date: Thu, 20 Feb 2025 17:59:55 GMT
• Title: Making Universal Policies Universal
• Authors: Niklas Höpner, David Kuric, Herke van Hoof,
• Abstract summary: We build on the universal policy framework, which decouples policy learning into two stages.<n>We propose a method for training the planner on a joint dataset composed of trajectories from all agents.<n>By training on a pooled dataset from multiple agents, our universal policy achieves an improvement of up to $42.20%$ in task completion accuracy.
• Score: 21.558271405324767
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of a generalist agent capable of solving a wide range of sequential decision-making tasks remains a significant challenge. We address this problem in a cross-agent setup where agents share the same observation space but differ in their action spaces. Our approach builds on the universal policy framework, which decouples policy learning into two stages: a diffusion-based planner that generates observation sequences and an inverse dynamics model that assigns actions to these plans. We propose a method for training the planner on a joint dataset composed of trajectories from all agents. This method offers the benefit of positive transfer by pooling data from different agents, while the primary challenge lies in adapting shared plans to each agent's unique constraints. We evaluate our approach on the BabyAI environment, covering tasks of varying complexity, and demonstrate positive transfer across agents. Additionally, we examine the planner's generalisation ability to unseen agents and compare our method to traditional imitation learning approaches. By training on a pooled dataset from multiple agents, our universal policy achieves an improvement of up to $42.20\%$ in task completion accuracy compared to a policy trained on a dataset from a single agent.

Related papers

• Uniting contrastive and generative learning for event sequences models [51.547576949425604]
  This study investigates the integration of two self-supervised learning techniques - instance-wise contrastive learning and a generative approach based on restoring masked events in latent space. Experiments conducted on several public datasets, focusing on sequence classification and next-event type prediction, show that the integrated method achieves superior performance compared to individual approaches.
  arXiv  Detail & Related papers  (2024-08-19T13:47:17Z)
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning [46.28771270378047]
  Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private reward function corresponding to different tasks, while sharing the same transition kernel of the environment. We learn a globally optimal policy that maximizes the sum of the discounted total rewards of all the agents in a decentralized manner.
  arXiv  Detail & Related papers  (2023-11-01T00:15:18Z)
• Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment [12.122881147337505]
  We propose a novel centralized training with decentralized execution method based on multi-agent reinforcement learning. In our approach, agents communicate only with the centralized planner to make decentralized decisions online. We conduct multi-step value convergence in multi-agent reinforcement learning to enhance the training efficiency.
  arXiv  Detail & Related papers  (2023-10-25T14:21:22Z)
• Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization [63.554226552130054]
  Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL) The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. We present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment.
  arXiv  Detail & Related papers  (2023-10-11T06:09:26Z)
• Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning [46.354187895184154]
  Multi-agent Pathfinding (MAPF) problem generally asks to find a set of conflict-free paths for a set of agents confined to a graph. In this work, we investigate the decentralized MAPF setting, when the central controller that posses all the information on the agents' locations and goals is absent. We focus on the practically important lifelong variant of MAPF, which involves continuously assigning new goals to the agents upon arrival to the previous ones.
  arXiv  Detail & Related papers  (2023-10-02T13:51:32Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)
• Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates [63.58053355357644]
  We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks. We show theoretically that having access to a specific set of diverse policies, which we call a set of independent policies, can allow for instantaneously achieving high-level performance.
  arXiv  Detail & Related papers  (2021-12-30T12:20:46Z)
• A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning [47.154539984501895]
  We propose a novel meta-multiagent policy gradient theorem that accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent's own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment.
  arXiv  Detail & Related papers  (2020-10-31T22:50:21Z)
• Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning [14.017603575774361]
  We formalize the notion of agent indication and prove that it enables convergence to optimal policies for the first time. Next, we formally introduce methods to extend parameter sharing to learning in heterogeneous observation and action spaces.
  arXiv  Detail & Related papers  (2020-05-27T20:14:28Z)
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous [66.6895109554163]
  Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
  arXiv  Detail & Related papers  (2020-03-15T19:49:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.