paper-with-me

Papers

Self-Predictive Universal AI

2023-09-21 · NeurIPS 2023 11

Reinforcement Learning (RL) algorithms typically utilize learning and/or planning techniques to derive effective policies. The integration of both approaches has proven to be highly successful in addressing complex sequential decision-making challenges, as evidenced by algorithms such as AlphaZero and MuZero, which consolidate the planning process into a parametric search-policy. AIXI, the most potent theoretical universal agent, leverages planning through comprehensive search as its primary means to find an optimal policy. Here we define an alternative universal agent, which we call Self-AIXI, that on the contrary to AIXI, maximally exploits learning to obtain good policies. It does so by self-predicting its own stream of action data, which is generated, similarly to other TD(0) agents, by taking an action maximization step over the current on-policy (universal mixture-policy) Q-value estimates. We prove that Self-AIXI converges to AIXI, and inherits a series of properties like maximal Legg-Hutter intelligence and the self-optimizing property.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Batch Normalization 설명 없음
Average Pooling 설명 없음
Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…
Monte-Carlo Tree Search Monte-Carlo Tree Search is a planning algorithm that accumulates value estimates obtained from Monte Carlo simulations in order to successively direct simulations towards more…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture

2024-07-15 · Dong-Hee Kim, Sungduk Cho, Hyeonwoo Cho, Chanmin Park 외

In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated with training segmentation models. Mask-…

DecoderImage SegmentationSegmentationSelf-Supervised Learning+1

Universal Supervised Learning for Individual Data

2018-12-22 · Yaniv Fogel, Meir Feder

Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where…

Revisiting the Relation Between Robustness and Universality

2025-10-22 · M. Klabunde, L. Caspari, F. Lemmerich arxiv

The modified universality hypothesis proposed by Jones et al. (2022) suggests that adversarially robust models trained for a given task are highly similar. We revisit the hypothesis and test its generality. While we veri…

A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement

2025-05-30 · Jie Zhang, Haoyin Yan, Xiaofei Li

It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning-based predictive methods, diffusion-bas…

DenoisingSpeech Enhancement

UniHPF : Universal Healthcare Predictive Framework with Zero Domain Knowledge

2022-11-15 · Kyunghoon Hur, JungWoo Oh, Junu Kim, Jiyoun Kim 외

Despite the abundance of Electronic Healthcare Records (EHR), its heterogeneity restricts the utilization of medical data in building predictive models. To address this challenge, we propose Universal Healthcare Predicti…