activity
20212026
most citedCORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents

9 citations · 16 across the 10 of their papers we have counts for

collaborators

10 papers

physics.gen-ph2026

Emergent Space, Time, and Lorentz Symmetry from Binary Sequences

Sam Powers, Dejan Stojkovic

We construct an information theory framework in which the fundamental objects are binary sequences of length , equipped with the bitwise XOR operation. The only physical observa…

physics.gen-ph2026

The quantum harmonic oscillator from binary sequences

Samuel Powers, Dino Skrgic, Dejan Stojkovic

The quantum harmonic oscillator (QHO) is normally built on a structure that contains a Hilbert space, ladder operators, and a Born rule. Here we derive it from counting. We adopt t…

cs.CL2025

Basis Vector Metric: A Method for Robust Open-Ended State Change Detection

David Oprea, Sam Powers

We test a new method, which we will abbreviate using the acronym BVM (Basis Vectors Method), in its ability to judge the state changes in images through using language embeddings.…

physics.gen-ph2023★ 1 cited

An event centric approach to modeling quantum systems

Sam Powers, Dejan Stojkovic

We define an event-centric framework for modeling quantum systems whose only modeling elements are classical bits. An event is a correlation between two binary sequences, one repre…

quant-ph2023★ 2 cited

A statistical model for quantum spin and photon number states

Sam Powers, Guangpeng Xu, Herbert Fotso +2

The most irreducible way to represent information is a sequence of two symbols. In this paper, we construct quantum states using this basic building block. Specifically, we show th…

cs.RO2023★ 1 cited

Spatial-Language Attention Policies for Efficient Robot Learning

Priyam Parashar, Vidhi Jain, Xiaohan Zhang +4

Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properti…

cs.LG2022

Self-Activating Neural Ensembles for Continual Reinforcement Learning

Sam Powers, Eliot Xing, Abhinav Gupta

The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intellig…

hep-th2022★ 1 cited

Quantum Gravity and Phenomenology: Dark Matter, Dark Energy, Vacuum Selection, Emergent Spacetime, and Wormholes

Per Berglund, De-Chang Dai, Douglas Edmonds +9

We discuss the relevance of quantum gravity to the frontier questions in high energy phenomenology: the problems of dark matter, dark energy, and vacuum selection as well as the pr…

quant-ph2021★ 2 cited

An alternative formalism for modeling spin

Sam Powers, Dejan Stojkovic

We present an alternative formalism for modeling spin. The ontological elements of this formalism are base-2 sequences of length . The machinery necessary to model physics is th…

cs.LG2021★ 9 cited

CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents

Sam Powers, Eliot Xing, Eric Kolve +2

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this…