ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning

• URL: http://arxiv.org/abs/2011.06777v1
• Date: Fri, 13 Nov 2020 06:21:56 GMT
• Title: ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning
• Authors: Yufei Wang, Gautham Narayan Narasimhan, Xingyu Lin, Brian Okorn, David Held
• Abstract summary: Current reinforcement learning algorithms operate on the whole image without performing object-level reasoning. In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. Our proposed algorithm, ROLL, learns dramatically faster and better final performance compared with previous methods in several simulated visual control tasks.
• Score: 16.18256739680704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning. This leads to inefficient goal sampling and ineffective reward functions. In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. Specifically, we use unknown object segmentation to ignore distractors in the scene for better reward computation and goal generation; we further enable occlusion reasoning by employing a novel auxiliary loss and training scheme. We demonstrate that our proposed algorithm, ROLL (Reinforcement learning with Object Level Learning), learns dramatically faster and achieves better final performance compared with previous methods in several simulated visual control tasks. Project video and code are available at https://sites.google.com/andrew.cmu.edu/roll.

Related papers

• RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback [24.759613248409167]
  Reward engineering has long been a challenge in Reinforcement Learning research. We propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains.
  arXiv  Detail & Related papers  (2024-02-06T04:06:06Z)
• An Invitation to Deep Reinforcement Learning [24.807012576054504]
  Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning. Common objectives like intersection over union (IoU), bilingual evaluation understudy (BLEU) score or rewards cannot be optimized with supervised learning. Reinforcement learning (RL) has emerged as a promising alternative for optimizing deep neural networks to maximize non-differentiable objectives.
  arXiv  Detail & Related papers  (2023-12-13T18:57:23Z)
• Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery [64.41455104593304]
  Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. We propose to adapt similar RL-based methods to unsupervised object discovery. We demonstrate that our approach is not only more accurate, but also orders of magnitudes faster to train.
  arXiv  Detail & Related papers  (2023-10-29T17:03:12Z)
• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience [89.30876995059168]
  inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. This paper addresses the problem of IRL -- inferring the reward function of an agent from observing its behavior.
  arXiv  Detail & Related papers  (2022-08-09T17:29:49Z)
• Depth-CUPRL: Depth-Imaged Contrastive Unsupervised Prioritized Representations in Reinforcement Learning for Mapless Navigation of Unmanned Aerial Vehicles [1.2468700211588883]
  Reinforcement Learning (RL) has presented an impressive performance in video games through raw pixel imaging and continuous control tasks. It is generally accepted that physical state-based RL policies such as laser sensor measurements give a more sample-efficient result than learning by pixels. This work presents a new approach that extracts information from a depth map estimation to teach an RL agent to perform the mapless navigation of Unmanned Aerial Vehicle (UAV)
  arXiv  Detail & Related papers  (2022-06-30T11:54:01Z)
• Contrastive Learning as Goal-Conditioned Reinforcement Learning [147.28638631734486]
  In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion is unstable. We show (contrastive) representation learning methods can be cast as RL algorithms in their own right.
  arXiv  Detail & Related papers  (2022-06-15T14:34:15Z)
• Unsupervised Object-Level Representation Learning from Scene Images [97.07686358706397]
  Object-level Representation Learning (ORL) is a new self-supervised learning framework towards scene images. Our key insight is to leverage image-level self-supervised pre-training as the prior to discover object-level semantic correspondence. ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks.
  arXiv  Detail & Related papers  (2021-06-22T17:51:24Z)
• Self-supervised Video Object Segmentation [76.83567326586162]
  The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking) We make the following contributions: (i) we propose to improve the existing self-supervised approach, with a simple, yet more effective memory mechanism for long-term correspondence matching; (ii) by augmenting the self-supervised approach with an online adaptation module, our method successfully alleviates tracker drifts caused by spatial-temporal discontinuity; (iv) we demonstrate state-of-the-art results among the self-supervised approaches on DAVIS-2017 and YouTube
  arXiv  Detail & Related papers  (2020-06-22T17:55:59Z)
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? [72.00712736992618]
  We show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
  arXiv  Detail & Related papers  (2020-03-25T17:58:42Z)
• Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping in Clutter by State Representation Learning Based on Disentanglement of a Raw Input Image [4.970364068620608]
  Actor-critic deep reinforcement learning (RL) methods typically perform very poorly when grasping diverse objects. We employ state representation learning (SRL), where we encode essential information first for subsequent use in RL. We found that preprocessing based on the disentanglement of a raw input image is the key to effectively capturing a compact representation.
  arXiv  Detail & Related papers  (2020-02-27T03:58:51Z)

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.