Understanding the origin of information-seeking exploration in probabilistic objectives for control

• URL: http://arxiv.org/abs/2103.06859v2
• Date: Sun, 14 Mar 2021 14:31:46 GMT
• Title: Understanding the origin of information-seeking exploration in probabilistic objectives for control
• Authors: Beren Millidge, Alexander Tschantz, Anil Seth, Christopher Buckley
• Abstract summary: An exploration-exploitation trade-off is central to the description of adaptive behaviour. One approach to solving this trade-off has been to equip or propose that agents possess an intrinsic 'exploratory drive' We show that this combination of utility maximizing and information-seeking behaviour arises from the minimization of an entirely difference class of objectives.
• Score: 62.997667081978825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The exploration-exploitation trade-off is central to the description of adaptive behaviour in fields ranging from machine learning, to biology, to economics. While many approaches have been taken, one approach to solving this trade-off has been to equip or propose that agents possess an intrinsic 'exploratory drive' which is often implemented in terms of maximizing the agents information gain about the world -- an approach which has been widely studied in machine learning and cognitive science. In this paper we mathematically investigate the nature and meaning of such approaches and demonstrate that this combination of utility maximizing and information-seeking behaviour arises from the minimization of an entirely difference class of objectives we call divergence objectives. We propose a dichotomy in the objective functions underlying adaptive behaviour between \emph{evidence} objectives, which correspond to well-known reward or utility maximizing objectives in the literature, and \emph{divergence} objectives which instead seek to minimize the divergence between the agent's expected and desired futures, and argue that this new class of divergence objectives could form the mathematical foundation for a much richer understanding of the exploratory components of adaptive and intelligent action, beyond simply greedy utility maximization.

Related papers

• Generative Intrinsic Optimization: Intrinsic Control with Model Learning [5.439020425819001]
  Future sequence represents the outcome after executing the action into the environment. Explicit outcomes may vary across state, return, or trajectory serving different purposes such as credit assignment or imitation learning. We propose a policy scheme that seamlessly incorporates the mutual information, ensuring convergence to the optimal policy.
  arXiv  Detail & Related papers  (2023-10-12T07:50:37Z)
• Generative multitask learning mitigates target-causing confounding [61.21582323566118]
  We propose a simple and scalable approach to causal representation learning for multitask learning. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. Our results on the Attributes of People and Taskonomy datasets reflect the conceptual improvement in robustness to prior probability shift.
  arXiv  Detail & Related papers  (2022-02-08T20:42:14Z)
• 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)
• The Value of Information When Deciding What to Learn [21.945359614094503]
  This work builds upon the seminal design principle of information-directed sampling (Russo & Van Roy, 2014) We offer new insights into learning targets from the literature on rate-distortion theory before turning to empirical results that confirm the value of information when deciding what to learn.
  arXiv  Detail & Related papers  (2021-10-26T19:23:12Z)
• Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning [15.33496710690063]
  We propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way. We then devise goal-discriminative attention networks (GDAN) which utilize the goal-relevant information to focus on the given instruction.
  arXiv  Detail & Related papers  (2021-10-25T14:24:39Z)
• Action and Perception as Divergence Minimization [43.75550755678525]
  Action Perception Divergence is an approach for categorizing the space of possible objective functions for embodied agents. We show a spectrum that reaches from narrow to general objectives. These agents use perception to align their beliefs with the world and use actions to align the world with their beliefs.
  arXiv  Detail & Related papers  (2020-09-03T16:52:46Z)
• Automatic Curriculum Learning through Value Disagreement [95.19299356298876]
  Continually solving new, unsolved tasks is the key to learning diverse behaviors. In the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. We propose setting up an automatic curriculum for goals that the agent needs to solve. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-17T03:58:25Z)
• Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning [102.05692309417047]
  In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals. We propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states.
  arXiv  Detail & Related papers  (2020-02-05T19:21:20Z)

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.