Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective

• URL: http://arxiv.org/abs/2305.18464v2
• Date: Mon, 14 Oct 2024 09:23:30 GMT
• Title: Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective
• Authors: Haoran He, Peilin Wu, Chenjia Bai, Hang Lai, Lingxiao Wang, Ling Pan, Xiaolin Hu, Weinan Zhang,
• Abstract summary: We propose a novel privileged knowledge distillation method called the Historical Information Bottleneck (HIB) HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods.
• Score: 38.845882541261645
• License:
• Abstract: Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the available privileged knowledge, resulting in suboptimal performance. In this paper, we formulate the sim-to-real gap as an information bottleneck problem and therefore propose a novel privileged knowledge distillation method called the Historical Information Bottleneck (HIB). In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods. Videos of real-world experiments are available at https://sites.google.com/view/history-ib .

Related papers

• On-Robot Bayesian Reinforcement Learning for POMDPs [16.667924736270415]
  This paper advances Bayesian reinforcement learning for robotics by proposing a specialized framework for physical systems. We capture this knowledge in a factored representation, then demonstrate the posterior factorizes in a similar shape, and ultimately formalize the model in a Bayesian framework. We then introduce a sample-based online solution method, based on Monte-Carlo tree search and particle filtering, specialized to solve the resulting model.
  arXiv  Detail & Related papers  (2023-07-22T01:16:29Z)
• 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)
• Explainability in reinforcement learning: perspective and position [1.299941371793082]
  This paper attempts to give a systematic overview of existing methods in the explainable RL area. It proposes a novel unified taxonomy, building and expanding on the existing ones.
  arXiv  Detail & Related papers  (2022-03-22T09:00:13Z)
• Robust Learning from Observation with Model Misspecification [33.92371002674386]
  Imitation learning (IL) is a popular paradigm for training policies in robotic systems. We propose a robust IL algorithm to learn policies that can effectively transfer to the real environment without fine-tuning.
  arXiv  Detail & Related papers  (2022-02-12T07:04:06Z)
• Practical Imitation Learning in the Real World via Task Consistency Loss [18.827979446629296]
  This paper introduces a self-supervised loss that encourages sim and real alignment both at the feature and action-prediction levels. We achieve 80% success across ten seen and unseen scenes using only 16.2 hours of teleoperated demonstrations in sim and real.
  arXiv  Detail & Related papers  (2022-02-03T21:43:06Z)
• Exploratory State Representation Learning [63.942632088208505]
  We propose a new approach called XSRL (eXploratory State Representation Learning) to solve the problems of exploration and SRL in parallel. On one hand, it jointly learns compact state representations and a state transition estimator which is used to remove unexploitable information from the representations. On the other hand, it continuously trains an inverse model, and adds to the prediction error of this model a $k$-step learning progress bonus to form the objective of a discovery policy.
  arXiv  Detail & Related papers  (2021-09-28T10:11:07Z)
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning [84.30765628008207]
  We propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. Our method outperforms the current state-of-the-art methods by a large margin on both benchmarks.
  arXiv  Detail & Related papers  (2021-06-08T07:37:37Z)
• Learning Dexterous Manipulation from Suboptimal Experts [69.8017067648129]
  Relative Entropy Q-Learning (REQ) is a simple policy algorithm that combines ideas from successful offline and conventional RL algorithms. We show how REQ is also effective for general off-policy RL, offline RL, and RL from demonstrations.
  arXiv  Detail & Related papers  (2020-10-16T18:48:49Z)
• Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey [0.07366405857677225]
  We cover the background behind sim-to-real transfer in deep reinforcement learning. We overview the main methods being utilized at the moment: domain randomization, domain adaptation, imitation learning, meta-learning and knowledge distillation.
  arXiv  Detail & Related papers  (2020-09-24T21:05:46Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)

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.