Multi-task Reinforcement Learning with a Planning Quasi-Metric

• URL: http://arxiv.org/abs/2002.03240v3
• Date: Sat, 5 Dec 2020 14:21:23 GMT
• Title: Multi-task Reinforcement Learning with a Planning Quasi-Metric
• Authors: Vincent Micheli, Karthigan Sinnathamby, Fran\c{c}ois Fleuret
• Abstract summary: We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator.
• Score: 0.49416305961918056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another, with task-specific "aimers" that compute a target state to reach a given goal. This decomposition allows the sharing across tasks of a task-agnostic model of the quasi-metric that captures the environment's dynamics and can be learned in a dense and unsupervised manner. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator.

Related papers

• MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation [52.739500459903724]
  Large Language Models (LLMs) have demonstrated remarkable planning abilities across various domains, including robotics manipulation and navigation. We propose a novel multi-agent LLM framework that distributes high-level planning and low-level control code generation across specialized LLM agents. We evaluate our approach on nine RLBench tasks, including long-horizon tasks, and demonstrate its ability to solve robotics manipulation in a zero-shot setting.
  arXiv  Detail & Related papers  (2024-11-26T17:53:44Z)
• Multi-Task Learning as a Bargaining Game [63.49888996291245]
  In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. We propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update.
  arXiv  Detail & Related papers  (2022-02-02T13:21:53Z)
• Curriculum Meta-Learning for Few-shot Classification [1.5039745292757671]
  We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification. Our experiments with the MAML algorithm on two few-shot image classification tasks show significant gains with the curriculum training framework.
  arXiv  Detail & Related papers  (2021-12-06T10:29:23Z)
• Distributed Mission Planning of Complex Tasks for Heterogeneous Multi-Robot Teams [2.329625852490423]
  We propose a distributed multi-stage optimization method for planning complex missions for heterogeneous multi-robot teams. The proposed approach involves a multi-objective search of the mission, represented as a hierarchical tree that defines the mission goal. We demonstrate the method's ability to adapt the planning strategy depending on the available robots and the given optimization criteria.
  arXiv  Detail & Related papers  (2021-09-21T11:36:11Z)
• Multi-Task Learning with Sequence-Conditioned Transporter Networks [67.57293592529517]
  We aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. We propose a new suite of benchmark aimed at compositional tasks, MultiRavens, which allows defining custom task combinations. Second, we propose a vision-based end-to-end system architecture, Sequence-Conditioned Transporter Networks, which augments Goal-Conditioned Transporter Networks with sequence-conditioning and weighted sampling.
  arXiv  Detail & Related papers  (2021-09-15T21:19:11Z)
• Meta-Learning with Fewer Tasks through Task Interpolation [67.03769747726666]
  Current meta-learning algorithms require a large number of meta-training tasks, which may not be accessible in real-world scenarios. By meta-learning with task gradient (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels. Empirically, in our experiments on eight datasets from diverse domains, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.
  arXiv  Detail & Related papers  (2021-06-04T20:15:34Z)
• Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent [79.58680275615752]
  We propose an energy-efficient federated meta-learning framework. We assume each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model.
  arXiv  Detail & Related papers  (2021-05-31T08:15:44Z)
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction [12.494209368988253]
  We propose a novel curriculum-meta learning method to tackle the challenges of continual relation extraction. We combine meta learning and curriculum learning to quickly adapt model parameters to a new task. We present novel difficulty-based metrics to quantitatively measure the extent of order-sensitivity of a given model.
  arXiv  Detail & Related papers  (2021-01-06T08:52:34Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)
• A Simple General Approach to Balance Task Difficulty in Multi-Task Learning [4.531240717484252]
  In multi-task learning, difficulty levels of different tasks are varying. We propose a Balanced Multi-Task Learning (BMTL) framework. The proposed BMTL framework is very simple and it can be combined with most multi-task learning models.
  arXiv  Detail & Related papers  (2020-02-12T04:31:34Z)

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.