A Dual Approach to Imitation Learning from Observations with Offline Datasets

• URL: http://arxiv.org/abs/2406.08805v1
• Date: Thu, 13 Jun 2024 04:39:42 GMT
• Title: A Dual Approach to Imitation Learning from Observations with Offline Datasets
• Authors: Harshit Sikchi, Caleb Chuck, Amy Zhang, Scott Niekum,
• Abstract summary: Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. We derive DILO, an algorithm that can leverage arbitrary suboptimal data to learn imitating policies without requiring expert actions.
• Score: 19.856363985916644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. However, demonstrating expert behavior in the action space of the agent becomes unwieldy when robots have complex, unintuitive morphologies. We consider the practical setting where an agent has a dataset of prior interactions with the environment and is provided with observation-only expert demonstrations. Typical learning from observations approaches have required either learning an inverse dynamics model or a discriminator as intermediate steps of training. Errors in these intermediate one-step models compound during downstream policy learning or deployment. We overcome these limitations by directly learning a multi-step utility function that quantifies how each action impacts the agent's divergence from the expert's visitation distribution. Using the principle of duality, we derive DILO(Dual Imitation Learning from Observations), an algorithm that can leverage arbitrary suboptimal data to learn imitating policies without requiring expert actions. DILO reduces the learning from observations problem to that of simply learning an actor and a critic, bearing similar complexity to vanilla offline RL. This allows DILO to gracefully scale to high dimensional observations, and demonstrate improved performance across the board. Project page (code and videos): $\href{https://hari-sikchi.github.io/dilo/}{\text{hari-sikchi.github.io/dilo/}}$

Related papers

• SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models [22.472167814814448]
  We propose a new model-based imitation learning algorithm named Separated Model-based Adversarial Imitation Learning (SeMAIL) Our method achieves near-expert performance on various visual control tasks with complex observations and the more challenging tasks with different backgrounds from expert observations.
  arXiv  Detail & Related papers  (2023-06-19T04:33:44Z)
• 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)
• Accelerating exploration and representation learning with offline pre-training [52.6912479800592]
  We show that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward can significantly improve the sample efficiency on the challenging NetHack benchmark.
  arXiv  Detail & Related papers  (2023-03-31T18:03:30Z)
• Contrastive Value Learning: Implicit Models for Simple Offline RL [40.95632543012637]
  We propose Contrastive Value Learning (CVL), which learns an implicit, multi-step model of the environment dynamics. CVL can be learned without access to reward functions, but nonetheless can be used to directly estimate the value of each action. Our experiments demonstrate that CVL outperforms prior offline RL methods on complex continuous control benchmarks.
  arXiv  Detail & Related papers  (2022-11-03T19:10:05Z)
• The Surprising Effectiveness of Representation Learning for Visual Imitation [12.60653315718265]
  We propose to decouple representation learning from behavior learning for visual imitation. First, we learn a visual representation encoder from offline data using standard supervised and self-supervised learning methods. We experimentally show that this simple decoupling improves the performance of visual imitation models on both offline demonstration datasets and real-robot door opening compared to prior work in visual imitation.
  arXiv  Detail & Related papers  (2021-12-02T18:58:09Z)
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
  arXiv  Detail & Related papers  (2021-06-10T17:59:13Z)
• Distill on the Go: Online knowledge distillation in self-supervised learning [1.1470070927586016]
  Recent works have shown that wider and deeper models benefit more from self-supervised learning than smaller models. We propose Distill-on-the-Go (DoGo), a self-supervised learning paradigm using single-stage online knowledge distillation. Our results show significant performance gain in the presence of noisy and limited labels.
  arXiv  Detail & Related papers  (2021-04-20T09:59:23Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)
• PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning [102.36450942613091]
  We propose an inverse reinforcement learning algorithm, called emphinverse temporal difference learning (ITD) We show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $Psi Phi$-learning.
  arXiv  Detail & Related papers  (2021-02-24T21:12:09Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.