no code implementations • 9 Feb 2024 • Wilka Carvalho, Momchil S. Tomov, William de Cothi, Caswell Barry, Samuel J. Gershman
Adaptive behavior often requires predicting future events.
1 code implementation • 13 Dec 2023 • Qihong Lu, Tan T. Nguyen, Qiong Zhang, Uri Hasson, Thomas L. Griffiths, Jeffrey M. Zacks, Samuel J. Gershman, Kenneth A. Norman
Through learning, it naturally stores structure that is shared across tasks in the network weights.
no code implementations • 5 Dec 2023 • Marcel Binz, Stephan Alaniz, Adina Roskies, Balazs Aczel, Carl T. Bergstrom, Colin Allen, Daniel Schad, Dirk Wulff, Jevin D. West, Qiong Zhang, Richard M. Shiffrin, Samuel J. Gershman, Ven Popov, Emily M. Bender, Marco Marelli, Matthew M. Botvinick, Zeynep Akata, Eric Schulz
For this opinion piece, we have invited four diverse groups of scientists to reflect on this query, sharing their perspectives and engaging in debate.
no code implementations • 9 Oct 2023 • Tanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan
We identify sufficient statistics for the test loss of such a network, and tracking these over training reveals that grokking arises in this setting when the network first attempts to fit a kernel regression solution with its initial features, followed by late-time feature learning where a generalizing solution is identified after train loss is already low.
no code implementations • NeurIPS 2023 • Changmin Yu, Neil Burgess, Maneesh Sahani, Samuel J. Gershman
Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with self-generated intrinsic rewards.
no code implementations • 11 Sep 2022 • Samuel J. Gershman
As an alternative, it has been proposed that molecules within the cell body are the storage sites of memory, and that memories are formed through biochemical operations on these molecules.
no code implementations • 27 Aug 2021 • William H. Alexander, Samuel J. Gershman
The Reward Prediction Error hypothesis proposes that phasic activity in the midbrain dopaminergic system reflects prediction errors needed for learning in reinforcement learning.
no code implementations • 27 Jul 2021 • Pedro A. Tsividis, Joao Loula, Jake Burga, Nathan Foss, Andres Campero, Thomas Pouncy, Samuel J. Gershman, Joshua B. Tenenbaum
Here we propose a new approach to this challenge based on a particularly strong form of model-based RL which we call Theory-Based Reinforcement Learning, because it uses human-like intuitive theories -- rich, abstract, causal models of physical objects, intentional agents, and their interactions -- to explore and model an environment, and plan effectively to achieve task goals.
no code implementations • ICLR 2022 • Tuan Anh Le, Katherine M. Collins, Luke Hewitt, Kevin Ellis, N. Siddharth, Samuel J. Gershman, Joshua B. Tenenbaum
We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization.
no code implementations • Findings (ACL) 2021 • Ruocheng Wang, Jiayuan Mao, Samuel J. Gershman, Jiajun Wu
These object-centric concepts derived from language facilitate the learning of object-centric representations.
1 code implementation • 12 Sep 2019 • Ishita Dasgupta, Demi Guo, Samuel J. Gershman, Noah D. Goodman
Analyzing performance on these diagnostic tests indicates a lack of systematicity in the representations and decision rules, and reveals a set of heuristic strategies.
no code implementations • 23 Jan 2019 • Samuel J. Gershman
The free energy principle has been proposed as a unifying account of brain function.
no code implementations • NeurIPS 2018 • Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, Finale Doshi-Velez
We often desire our models to be interpretable as well as accurate.
no code implementations • 18 Feb 2018 • Zoran Tiganj, Samuel J. Gershman, Per B. Sederberg, Marc W. Howard
Widely used reinforcement learning algorithms discretize continuous time and estimate either transition functions from one step to the next (model-based algorithms) or a scalar value of exponentially-discounted future reward using the Bellman equation (model-free algorithms).
1 code implementation • 12 Feb 2018 • Ishita Dasgupta, Demi Guo, Andreas Stuhlmüller, Samuel J. Gershman, Noah D. Goodman
Further, we find that augmenting training with our dataset improves test performance on our dataset without loss of performance on the original training dataset.
no code implementations • NeurIPS 2016 • Eric Schulz, Josh Tenenbaum, David K. Duvenaud, Maarten Speekenbrink, Samuel J. Gershman
How do people learn about complex functional structure?
1 code implementation • 8 Jun 2016 • Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam, Samuel J. Gershman
The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards.
no code implementations • 1 Apr 2016 • Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people.
no code implementations • NeurIPS 2014 • Kimberly L. Stachenfeld, Matthew Botvinick, Samuel J. Gershman
Furthermore, we demonstrate that this representation of space can support efficient reinforcement learning.
Hierarchical Reinforcement Learning reinforcement-learning +1