Transferring Knowledge for Reinforcement Learning in Contact-Rich
Manipulation
- URL: http://arxiv.org/abs/2210.02891v1
- Date: Mon, 19 Sep 2022 10:31:13 GMT
- Title: Transferring Knowledge for Reinforcement Learning in Contact-Rich
Manipulation
- Authors: Quantao Yang, Johannes A. Stork, and Todor Stoyanov
- Abstract summary: We address the challenge of transferring knowledge within a family of similar tasks by leveraging multiple skill priors.
Our method learns a latent action space representing the skill embedding from demonstrated trajectories for each prior task.
We have evaluated our method on a set of peg-in-hole insertion tasks and demonstrate better generalization to new tasks that have never been encountered during training.
- Score: 10.219833196479142
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In manufacturing, assembly tasks have been a challenge for learning
algorithms due to variant dynamics of different environments. Reinforcement
learning (RL) is a promising framework to automatically learn these tasks, yet
it is still not easy to apply a learned policy or skill, that is the ability of
solving a task, to a similar environment even if the deployment conditions are
only slightly different. In this paper, we address the challenge of
transferring knowledge within a family of similar tasks by leveraging multiple
skill priors. We propose to learn prior distribution over the specific skill
required to accomplish each task and compose the family of skill priors to
guide learning the policy for a new task by comparing the similarity between
the target task and the prior ones. Our method learns a latent action space
representing the skill embedding from demonstrated trajectories for each prior
task. We have evaluated our method on a set of peg-in-hole insertion tasks and
demonstrate better generalization to new tasks that have never been encountered
during training.
Related papers
- Reinforcement Learning with Success Induced Task Prioritization [68.8204255655161]
We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning.
The algorithm selects the order of tasks that provide the fastest learning for agents.
We demonstrate that SITP matches or surpasses the results of other curriculum design methods.
arXiv Detail & Related papers (2022-12-30T12:32:43Z) - Active Task Randomization: Learning Robust Skills via Unsupervised
Generation of Diverse and Feasible Tasks [37.73239471412444]
We introduce Active Task Randomization (ATR), an approach that learns robust skills through the unsupervised generation of training tasks.
ATR selects suitable tasks, which consist of an initial environment state and manipulation goal, for learning robust skills by balancing the diversity and feasibility of the tasks.
We demonstrate that the learned skills can be composed by a task planner to solve unseen sequential manipulation problems based on visual inputs.
arXiv Detail & Related papers (2022-11-11T11:24:55Z) - Saliency-Regularized Deep Multi-Task Learning [7.3810864598379755]
Multitask learning enforces multiple learning tasks to share knowledge to improve their generalization abilities.
Modern deep multitask learning can jointly learn latent features and task sharing, but they are obscure in task relation.
This paper proposes a new multitask learning framework that jointly learns latent features and explicit task relations.
arXiv Detail & Related papers (2022-07-03T20:26:44Z) - Multi-Agent Policy Transfer via Task Relationship Modeling [28.421365805638953]
We try to discover and exploit common structures among tasks for more efficient transfer.
We propose to learn effect-based task representations as a common space of tasks, using an alternatively fixed training scheme.
As a result, the proposed method can help transfer learned cooperation knowledge to new tasks after training on a few source tasks.
arXiv Detail & Related papers (2022-03-09T01:49:21Z) - Rethinking Learning Dynamics in RL using Adversarial Networks [79.56118674435844]
We present a learning mechanism for reinforcement learning of closely related skills parameterized via a skill embedding space.
The main contribution of our work is to formulate an adversarial training regime for reinforcement learning with the help of entropy-regularized policy gradient formulation.
arXiv Detail & Related papers (2022-01-27T19:51:09Z) - Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks [18.679936596282847]
No technique has been proposed to learn a sequence of mixed similar and dissimilar tasks that can deal with forgetting.
This paper proposes such a technique to learn both types of tasks in the same network.
For dissimilar tasks, the algorithm focuses on dealing with forgetting, and for similar tasks, the algorithm focuses on selectively transferring the knowledge learned from some similar previous tasks to improve the new task learning.
arXiv Detail & Related papers (2021-12-18T22:37:30Z) - Hierarchical Skills for Efficient Exploration [70.62309286348057]
In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration.
Prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design.
We propose a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner.
arXiv Detail & Related papers (2021-10-20T22:29:32Z) - Discovering Generalizable Skills via Automated Generation of Diverse
Tasks [82.16392072211337]
We propose a method to discover generalizable skills via automated generation of a diverse set of tasks.
As opposed to prior work on unsupervised discovery of skills, our method pairs each skill with a unique task produced by a trainable task generator.
A task discriminator defined on the robot behaviors in the generated tasks is jointly trained to estimate the evidence lower bound of the diversity objective.
The learned skills can then be composed in a hierarchical reinforcement learning algorithm to solve unseen target tasks.
arXiv Detail & Related papers (2021-06-26T03:41:51Z) - Latent Skill Planning for Exploration and Transfer [49.25525932162891]
In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent.
We leverage the idea of partial amortization for fast adaptation at test time.
We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks.
arXiv Detail & Related papers (2020-11-27T18:40:03Z) - Adaptive Procedural Task Generation for Hard-Exploration Problems [78.20918366839399]
We introduce Adaptive Procedural Task Generation (APT-Gen) to facilitate reinforcement learning in hard-exploration problems.
At the heart of our approach is a task generator that learns to create tasks from a parameterized task space via a black-box procedural generation module.
To enable curriculum learning in the absence of a direct indicator of learning progress, we propose to train the task generator by balancing the agent's performance in the generated tasks and the similarity to the target tasks.
arXiv Detail & Related papers (2020-07-01T09:38:51Z)
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.