Learning to Identify Critical States for Reinforcement Learning from Videos

• URL: http://arxiv.org/abs/2308.07795v1
• Date: Tue, 15 Aug 2023 14:21:24 GMT
• Title: Learning to Identify Critical States for Reinforcement Learning from Videos
• Authors: Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, J\"urgen Schmidhuber
• Abstract summary: Algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or robots may convey a lot of implicit information about rewarding action sequences. A DRL machine that wants to profit from watching such videos must first learn by itself to identify and recognize relevant states/actions/rewards.
• Score: 55.75825780842156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or robots may convey a lot of implicit information about rewarding action sequences, but a DRL machine that wants to profit from watching such videos must first learn by itself to identify and recognize relevant states/actions/rewards. Without relying on ground-truth annotations, our new method called Deep State Identifier learns to predict returns from episodes encoded as videos. Then it uses a kind of mask-based sensitivity analysis to extract/identify important critical states. Extensive experiments showcase our method's potential for understanding and improving agent behavior. The source code and the generated datasets are available at https://github.com/AI-Initiative-KAUST/VideoRLCS.

Related papers

• Extracting Unlearned Information from LLMs with Activation Steering [46.16882599881247]
  Unlearning has emerged as a solution to remove sensitive knowledge from models after training. We propose activation steering as a method for exact information retrieval from unlearned models. Our results demonstrate that exact information retrieval from unlearned models is possible, highlighting a severe vulnerability of current unlearning techniques.
  arXiv  Detail & Related papers  (2024-11-04T21:42:56Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Robotic Offline RL from Internet Videos via Value-Function Pre-Training [67.44673316943475]
  We develop a system for leveraging large-scale human video datasets in robotic offline RL. We show that value learning on video datasets learns representations more conducive to downstream robotic offline RL than other approaches.
  arXiv  Detail & Related papers  (2023-09-22T17:59:14Z)
• Reinforcement Learning from Passive Data via Latent Intentions [86.4969514480008]
  We show that passive data can still be used to learn features that accelerate downstream RL. Our approach learns from passive data by modeling intentions. Our experiments demonstrate the ability to learn from many forms of passive data, including cross-embodiment video data and YouTube videos.
  arXiv  Detail & Related papers  (2023-04-10T17:59:05Z)
• Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts [89.06560404218028]
  We introduce a new method for pre-training video action recognition models using queried web videos. Instead of trying to filter out, we propose to convert the potential noises in these queried videos to useful supervision signals. We show that SPL outperforms several existing pre-training strategies using pseudo-labels.
  arXiv  Detail & Related papers  (2021-01-11T05:50:16Z)
• A Comprehensive Study of Deep Video Action Recognition [35.7068977497202]
  Video action recognition is one of the representative tasks for video understanding. We provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition.
  arXiv  Detail & Related papers  (2020-12-11T18:54:08Z)
• Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues [75.1731999380562]
  We present a learning-based method for detecting real and fake deepfake multimedia content. We extract and analyze the similarity between the two audio and visual modalities from within the same video. We compare our approach with several SOTA deepfake detection methods and report per-video AUC of 84.4% on the DFDC and 96.6% on the DF-TIMIT datasets.
  arXiv  Detail & Related papers  (2020-03-14T22:07:26Z)

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.