Picture for Isaac Tamblyn

Isaac Tamblyn

National Research Council of Canada, Ottawa, ON, Canada, Vector Institute for Artificial Intelligence, Toronto, ON, Canada

Learning when to observe: A frugal reinforcement learning framework for a high-cost world

Add code
Jul 24, 2023
Viaarxiv icon

ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry

Add code
May 23, 2023
Figure 1 for ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry
Figure 2 for ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry
Figure 3 for ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry
Figure 4 for ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry
Viaarxiv icon

fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems

Add code
Jan 04, 2023
Figure 1 for fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems
Figure 2 for fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems
Figure 3 for fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems
Figure 4 for fintech-kMC: Agent based simulations of financial platforms for design and testing of machine learning systems
Viaarxiv icon

Training neural networks using Metropolis Monte Carlo and an adaptive variant

Add code
May 16, 2022
Figure 1 for Training neural networks using Metropolis Monte Carlo and an adaptive variant
Figure 2 for Training neural networks using Metropolis Monte Carlo and an adaptive variant
Figure 3 for Training neural networks using Metropolis Monte Carlo and an adaptive variant
Figure 4 for Training neural networks using Metropolis Monte Carlo and an adaptive variant
Viaarxiv icon

Machine Learning Diffusion Monte Carlo Energy Densities

Add code
May 09, 2022
Figure 1 for Machine Learning Diffusion Monte Carlo Energy Densities
Figure 2 for Machine Learning Diffusion Monte Carlo Energy Densities
Figure 3 for Machine Learning Diffusion Monte Carlo Energy Densities
Figure 4 for Machine Learning Diffusion Monte Carlo Energy Densities
Viaarxiv icon

Cellular automata can classify data by inducing trajectory phase coexistence

Add code
Apr 06, 2022
Figure 1 for Cellular automata can classify data by inducing trajectory phase coexistence
Figure 2 for Cellular automata can classify data by inducing trajectory phase coexistence
Figure 3 for Cellular automata can classify data by inducing trajectory phase coexistence
Viaarxiv icon

Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge

Add code
Apr 05, 2022
Figure 1 for Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge
Figure 2 for Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge
Figure 3 for Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge
Viaarxiv icon

Learning stochastic dynamics and predicting emergent behavior using transformers

Add code
Feb 17, 2022
Figure 1 for Learning stochastic dynamics and predicting emergent behavior using transformers
Figure 2 for Learning stochastic dynamics and predicting emergent behavior using transformers
Figure 3 for Learning stochastic dynamics and predicting emergent behavior using transformers
Figure 4 for Learning stochastic dynamics and predicting emergent behavior using transformers
Viaarxiv icon

Dynamic programming with partial information to overcome navigational uncertainty in a nautical environment

Add code
Dec 29, 2021
Figure 1 for Dynamic programming with partial information to overcome navigational uncertainty in a nautical environment
Figure 2 for Dynamic programming with partial information to overcome navigational uncertainty in a nautical environment
Figure 3 for Dynamic programming with partial information to overcome navigational uncertainty in a nautical environment
Figure 4 for Dynamic programming with partial information to overcome navigational uncertainty in a nautical environment
Viaarxiv icon

Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning

Add code
Dec 14, 2021
Figure 1 for Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning
Figure 2 for Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning
Figure 3 for Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning
Figure 4 for Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning
Viaarxiv icon