On the Sensory Commutativity of Action Sequences for Embodied Agents

• URL: http://arxiv.org/abs/2002.05630v3
• Date: Fri, 29 Jan 2021 10:15:08 GMT
• Title: On the Sensory Commutativity of Action Sequences for Embodied Agents
• Authors: Hugo Caselles-Dupr\'e, Michael Garcia-Ortiz, David Filliat
• Abstract summary: We study perception for embodied agents under the mathematical formalism of group theory. We introduce the Sensory Commutativity Probability criterion which measures how much an agent's degree of freedom affects the environment. We empirically illustrate how SCP and the commutative properties of action sequences can be used to learn about objects in the environment.
• Score: 2.320417845168326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Perception of artificial agents is one the grand challenges of AI research. Deep Learning and data-driven approaches are successful on constrained problems where perception can be learned using supervision, but do not scale to open-worlds. In such case, for autonomous embodied agents with first-person sensors, perception can be learned end-to-end to solve particular tasks. However, literature shows that perception is not a purely passive compression mechanism, and that actions play an important role in the formulation of abstract representations. We propose to study perception for these embodied agents, under the mathematical formalism of group theory in order to make the link between perception and action. In particular, we consider the commutative properties of continuous action sequences with respect to sensory information perceived by such an embodied agent. We introduce the Sensory Commutativity Probability (SCP) criterion which measures how much an agent's degree of freedom affects the environment in embodied scenarios. We show how to compute this criterion in different environments, including realistic robotic setups. We empirically illustrate how SCP and the commutative properties of action sequences can be used to learn about objects in the environment and improve sample-efficiency in Reinforcement Learning.

Related papers

• Exploring Action-Centric Representations Through the Lens of Rate-Distortion Theory [7.945169878921404]
  We argue that action-centric representations are efficient lossy compressions of the data. We conclude that full reconstruction of the data is rarely needed to achieve optimal behaviour.
  arXiv  Detail & Related papers  (2024-09-13T15:07:22Z)
• Learning Geometric Representations of Objects via Interaction [25.383613570119266]
  We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. We propose a representation learning framework extracting the location in physical space of both the agent and the object from unstructured observations of arbitrary nature.
  arXiv  Detail & Related papers  (2023-09-11T09:45:22Z)
• Imitation from Observation With Bootstrapped Contrastive Learning [12.048166025000976]
  Imitation from observation (IfO) is a learning paradigm that consists of training autonomous agents in a Markov Decision Process. We present BootIfOL, an IfO algorithm that aims to learn a reward function that takes an agent trajectory and compares it to an expert. We evaluate our approach on a variety of control tasks showing that we can train effective policies using a limited number of demonstrative trajectories.
  arXiv  Detail & Related papers  (2023-02-13T17:32:17Z)
• Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task [50.72283841720014]
  We propose a novel learning strategy that can improve reasoning about the effects of actions. We demonstrate the effectiveness of our proposed approach and discuss its advantages over previous baselines in terms of performance, data efficiency, and generalization capability.
  arXiv  Detail & Related papers  (2022-12-07T05:41:58Z)
• Interpreting Neural Policies with Disentangled Tree Representations [58.769048492254555]
  We study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation for disentanglement in robot learning. We introduce interpretability metrics that measure disentanglement of learned neural dynamics.
  arXiv  Detail & Related papers  (2022-10-13T01:10:41Z)
• Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions [51.71245032890532]
  We propose methods enabling an agent acting upon the world to learn internal representations of sensory information consistent with actions that modify it. In contrast to existing work, our approach does not require prior knowledge of the group and does not restrict the set of actions the agent can perform.
  arXiv  Detail & Related papers  (2022-07-25T11:22:48Z)
• Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams [64.82800502603138]
  This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
  arXiv  Detail & Related papers  (2022-04-26T09:52:31Z)
• Learning Intuitive Policies Using Action Features [7.260481131198059]
  We investigate the effect of network architecture on the propensity of learning algorithms to exploit semantic relationships. We find that attention-based architectures that jointly process a featurized representation of observations and actions have a better inductive bias for learning intuitive policies.
  arXiv  Detail & Related papers  (2022-01-29T20:54:52Z)
• Information is Power: Intrinsic Control via Information Capture [110.3143711650806]
  We argue that a compact and general learning objective is to minimize the entropy of the agent's state visitation estimated using a latent state-space model. This objective induces an agent to both gather information about its environment, corresponding to reducing uncertainty, and to gain control over its environment, corresponding to reducing the unpredictability of future world states.
  arXiv  Detail & Related papers  (2021-12-07T18:50:42Z)
• Modelling Behaviour Change using Cognitive Agent Simulations [0.0]
  This paper presents work-in-progress research to apply selected behaviour change theories to simulated agents. The research is focusing on complex agent architectures required for self-determined goal achievement in adverse circumstances.
  arXiv  Detail & Related papers  (2021-10-16T19:19:08Z)
• Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
  We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
  arXiv  Detail & Related papers  (2021-07-10T19:02:27Z)

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.