Search Results for author:
Found 28 papers, 14 papers with code
A Monte Carlo AIXI Approximation
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent.
General Reinforcement Learning
Open-Ended Question Answering
+2
Bootstrapping from Game Tree Search
We implemented our algorithm in a chess program Meep, using a linear heuristic function.
Reinforcement Learning via AIXI Approximation
This paper introduces a principled approach for the design of a scalable general reinforcement learning agent.
General Reinforcement Learning
Open-Ended Question Answering
+2
Monte-Carlo Planning in Large POMDPs
Our Monte-Carlo planning algorithm achieved a high level of performance with no prior knowledge, and was also able to exploit simple domain knowledge to achieve better results with less search.
Context Tree Switching
This paper describes the Context Tree Switching technique, a modification of Context Tree Weighting for the prediction of binary, stationary, n-Markov sources.
Information Theory Information Theory
Variance Reduction in Monte-Carlo Tree Search
Monte-Carlo Tree Search (MCTS) has proven to be a powerful, generic planning technique for decision-making in single-agent and adversarial environments.
The Arcade Learning Environment: An Evaluation Platform for General Agents
We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning.
Ranked #1 on
Atari Games
on Atari 2600 Pooyan
Sketch-Based Linear Value Function Approximation
Unfortunately, the typical use of hashing in value function approximation results in biased value estimates due to the possibility of collisions.
Online Learning of k-CNF Boolean Functions
This paper revisits the problem of learning a k-CNF Boolean function from examples in the context of online learning under the logarithmic loss.
Compress and Control
This paper describes a new information-theoretic policy evaluation technique for reinforcement learning.
Human level control through deep reinforcement learning
We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.
The Forget-me-not Process
We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources.
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
Ranked #3 on
Continual Learning
on F-CelebA (10 tasks)
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games.
Online Learning with Gated Linear Networks
This paper describes a family of probabilistic architectures designed for online learning under the logarithmic loss.
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
Gated Linear Networks
This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs).
Online Learning in Contextual Bandits using Gated Linear Networks
We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB).
Gaussian Gated Linear Networks
We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks.
A Combinatorial Perspective on Transfer Learning
Our main postulate is that the combination of task segmentation, modular learning and memory-based ensembling can give rise to generalization on an exponentially growing number of unseen tasks.
Reinforcement Learning with Information-Theoretic Actuation
In this work we explore and formalize a contrasting view, namely that actions are best thought of as the output of a sequence of internal choices with respect to an action model.
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
Neural Networks and the Chomsky Hierarchy
Reliable generalization lies at the heart of safe ML and AI.
Beyond Bayes-optimality: meta-learning what you know you don't know
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
Memory-Based Meta-Learning on Non-Stationary Distributions
Memory-based meta-learning is a technique for approximating Bayes-optimal predictors.
Randomized Positional Encodings Boost Length Generalization of Transformers
Transformers have impressive generalization capabilities on tasks with a fixed context length.
Language Modeling Is Compression
We show that large language models are powerful general-purpose predictors and that the compression viewpoint provides novel insights into scaling laws, tokenization, and in-context learning.
Learning Universal Predictors
Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data.
