Harnessing Discrete Representations For Continual Reinforcement Learning

• URL: http://arxiv.org/abs/2312.01203v3
• Date: Sat, 13 Jul 2024 06:47:10 GMT
• Title: Harnessing Discrete Representations For Continual Reinforcement Learning
• Authors: Edan Meyer, Adam White, Marlos C. Machado,
• Abstract summary: We investigate the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We find that, when compared to traditional continuous representations, world models learned over discrete representations accurately model more of the world with less capacity.
• Score: 8.61539229796467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perform evaluations on world-model learning, model-free RL, and ultimately continual RL problems, where the benefits best align with the needs of the problem setting. We find that, when compared to traditional continuous representations, world models learned over discrete representations accurately model more of the world with less capacity, and that agents trained with discrete representations learn better policies with less data. In the context of continual RL, these benefits translate into faster adapting agents. Additionally, our analysis suggests that the observed performance improvements can be attributed to the information contained within the latent vectors and potentially the encoding of the discrete representation itself.

Related papers

• Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning [57.67629402360924]
  We introduce the Partially Supervised Reinforcement Learning (PSRL) framework. At the heart of PSRL is the fusion of both supervised and unsupervised learning. We show that PSRL offers a potent balance, enhancing model interpretability while preserving, and often significantly outperforming, the performance benchmarks set by traditional methods.
  arXiv  Detail & Related papers  (2024-02-14T16:23:23Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison [0.0]
  This study compares common auxiliary tasks based on, to the best of our knowledge, the only decoupled representation learning method for low-dimensional non-visual observations. Our findings show that representation learning with auxiliary tasks only provides performance gains in sufficiently complex environments.
  arXiv  Detail & Related papers  (2023-10-06T13:22:26Z)
• Light-weight probing of unsupervised representations for Reinforcement Learning [20.638410483549706]
  We study whether linear probing can be a proxy evaluation task for the quality of unsupervised RL representation. We show that the probing tasks are strongly rank correlated with the downstream RL performance on the Atari100k Benchmark. This provides a more efficient method for exploring the space of pretraining algorithms and identifying promising pretraining recipes.
  arXiv  Detail & Related papers  (2022-08-25T21:08:01Z)
• Generalizable Information Theoretic Causal Representation [37.54158138447033]
  We propose to learn causal representation from observational data by regularizing the learning procedure with mutual information measures according to our hypothetical causal graph. The optimization involves a counterfactual loss, based on which we deduce a theoretical guarantee that the causality-inspired learning is with reduced sample complexity and better generalization ability.
  arXiv  Detail & Related papers  (2022-02-17T00:38:35Z)
• Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning [3.308743964406687]
  $k$-Step Latent (KSL) is a representation learning method that enforces temporal consistency of representations. KSL produces encoders that generalize better to new tasks unseen during training.
  arXiv  Detail & Related papers  (2021-10-11T00:16:43Z)
• 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)
• Desiderata for Representation Learning: A Causal Perspective [104.3711759578494]
  We take a causal perspective on representation learning, formalizing non-spuriousness and efficiency (in supervised representation learning) and disentanglement (in unsupervised representation learning) This yields computable metrics that can be used to assess the degree to which representations satisfy the desiderata of interest and learn non-spurious and disentangled representations from single observational datasets.
  arXiv  Detail & Related papers  (2021-09-08T17:33:54Z)
• Which Mutual-Information Representation Learning Objectives are Sufficient for Control? [80.2534918595143]
  Mutual information provides an appealing formalism for learning representations of data. This paper formalizes the sufficiency of a state representation for learning and representing the optimal policy. Surprisingly, we find that two of these objectives can yield insufficient representations given mild and common assumptions on the structure of the MDP.
  arXiv  Detail & Related papers  (2021-06-14T10:12:34Z)
• Odd-One-Out Representation Learning [1.6822770693792826]
  We show that a weakly-supervised downstream task based on odd-one-out observations is suitable for model selection. We also show that a bespoke metric-learning VAE model which performs highly on this task also out-performs other standard unsupervised and a weakly-supervised disentanglement model.
  arXiv  Detail & Related papers  (2020-12-14T22:01:15Z)
• Weakly-Supervised Disentanglement Without Compromises [53.55580957483103]
  Intelligent agents should be able to learn useful representations by observing changes in their environment. We model such observations as pairs of non-i.i.d. images sharing at least one of the underlying factors of variation. We show that only knowing how many factors have changed, but not which ones, is sufficient to learn disentangled representations.
  arXiv  Detail & Related papers  (2020-02-07T16:39:31Z)

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.