Related papers: Empowerment -- an Introduction
This paper develops generalizations of empowerment to continuous states. Empowerment is a recently introduced information-theoretic quantity motivated by hypotheses about the efficiency of the sensorimotor loop in biological organisms, but…
Information-theoretic fitness functions are becoming increasingly popular to produce generally useful, task-independent behaviors. One such universal function, dubbed empowerment, measures the amount of control an agent exerts on its…
Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for reinforcement learning (RL). Besides for unsupervised RL and…
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control. Empowerment, being the channel capacity between actions and…
Empowerment quantifies the influence an agent has on its environment. This is formally achieved by the maximum of the expected KL-divergence between the distribution of the successor state conditioned on a specific action and a distribution…
The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack…
Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity is captured by empowerment, which has served as a vital framing concept across artificial…
In a strategy-proof mechanism, the influence of an agent may be measured as the set of outcomes an agent can bring about by varying her (reported) type. More specifically, we refer to an agent's influence on her own relevant outcomes as her…
One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide…
A key aspect of a robot's knowledge base is self-awareness about what it is capable of doing. It allows to define which tasks it can be assigned to and which it cannot. We will refer to this knowledge as the Capability concept. As…
The concept of power can be explored at several scales: from physical action and process effectuation, all the way to complex social dynamics. A spectrum-wide analysis of power requires attention to the fundamental principles that constrain…
"Intrinsic motivation" refers to the capacity for intelligent systems to be motivated endogenously, i.e. by features of agential architecture itself rather than by learned associations between action and reward. This paper views active…
Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one…
Options represent a framework for reasoning across multiple time scales in reinforcement learning (RL). With the recent active interest in the unsupervised learning paradigm in the RL research community, the option framework was adapted to…
Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the…
As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually designed benchmarks. We propose information-theoretic…
Although there are many approaches to implement intrinsically motivated artificial agents, the combined usage of multiple intrinsic drives remains still a relatively unexplored research area. Specifically, we hypothesize that a mechanism…
Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents.…
Exploration is a difficult challenge in reinforcement learning and is of prime importance in sparse reward environments. However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on…
Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in artificial agents is concerned with the following question:…