Equivariant Reinforcement Learning under Partial Observability
- URL: http://arxiv.org/abs/2408.14336v1
- Date: Mon, 26 Aug 2024 15:07:01 GMT
- Title: Equivariant Reinforcement Learning under Partial Observability
- Authors: Hai Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato,
- Abstract summary: This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning.
Our actor-critic reinforcement learning agents can reuse solutions in the past for related scenarios.
- Score: 18.87759041528553
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivariance regarding specific group symmetries into the neural networks, our actor-critic reinforcement learning agents can reuse solutions in the past for related scenarios. Consequently, our equivariant agents outperform non-equivariant approaches significantly in terms of sample efficiency and final performance, demonstrated through experiments on a range of robotic tasks in simulation and real hardware.
Related papers
- Approximate Equivariance in Reinforcement Learning [35.04248486334824]
Equivariant neural networks have shown great success in reinforcement learning.
In many problems, only approximate symmetry is present, which makes imposing exact symmetry inappropriate.
We develop approximately equivariant algorithms in reinforcement learning.
arXiv Detail & Related papers (2024-11-06T19:44:46Z) - Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning [5.69473229553916]
This paper proposes a method to construct equivariant policies and invariant value functions without specialized neural network components.
We show how equivariant ensembles and regularization benefit sample efficiency and performance.
arXiv Detail & Related papers (2024-03-19T16:01:25Z) - The Common Stability Mechanism behind most Self-Supervised Learning
Approaches [64.40701218561921]
We provide a framework to explain the stability mechanism of different self-supervised learning techniques.
We discuss the working mechanism of contrastive techniques like SimCLR, non-contrastive techniques like BYOL, SWAV, SimSiam, Barlow Twins, and DINO.
We formulate different hypotheses and test them using the Imagenet100 dataset.
arXiv Detail & Related papers (2024-02-22T20:36:24Z) - Learning invariant representations of time-homogeneous stochastic dynamical systems [27.127773672738535]
We study the problem of learning a representation of the state that faithfully captures its dynamics.
This is instrumental to learning the transfer operator or the generator of the system.
We show that the search for a good representation can be cast as an optimization problem over neural networks.
arXiv Detail & Related papers (2023-07-19T11:32:24Z) - End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures.
We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
arXiv Detail & Related papers (2023-05-25T10:58:46Z) - The Surprising Effectiveness of Equivariant Models in Domains with
Latent Symmetry [6.716931832076628]
We show that imposing symmetry constraints that do not exactly match the domain symmetry is very helpful in learning the true symmetry in the environment.
We demonstrate that an equivariant model can significantly outperform non-equivariant methods on domains with latent symmetries both in supervised learning and in reinforcement learning for robotic manipulation and control problems.
arXiv Detail & Related papers (2022-11-16T21:51:55Z) - Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
In this work we provide a causal perspective and a new algorithm for learning invariant representations.
Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
arXiv Detail & Related papers (2022-06-23T12:06:54Z) - HyperImpute: Generalized Iterative Imputation with Automatic Model
Selection [77.86861638371926]
We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models.
We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
arXiv Detail & Related papers (2022-06-15T19:10:35Z) - Equivariance Allows Handling Multiple Nuisance Variables When Analyzing
Pooled Neuroimaging Datasets [53.34152466646884]
In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution.
We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
arXiv Detail & Related papers (2022-03-29T04:54:06Z) - Exploring Complementary Strengths of Invariant and Equivariant
Representations for Few-Shot Learning [96.75889543560497]
In many real-world problems, collecting a large number of labeled samples is infeasible.
Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples.
We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
arXiv Detail & Related papers (2021-03-01T21:14:33Z) - Group Equivariant Deep Reinforcement Learning [4.997686360064921]
We propose the use of Equivariant CNNs to train RL agents and study their inductive bias for transformation equivariant Q-value approximation.
We demonstrate that equivariant architectures can dramatically enhance the performance and sample efficiency of RL agents in a highly symmetric environment.
arXiv Detail & Related papers (2020-07-01T02:38:48Z)
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.