This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Workshop: Biological and Artificial Reinforcement Learning

Raymond Chua, Feryal Behbahani, Julie J Lee, Sara Zannone, Rui Ponte Costa, Blake Richards , Ida Momennejad, Doina Precup

2020-12-12T04:30:00-08:00 - 2020-12-12T15:45:00-08:00
Abstract: Reinforcement learning (RL) algorithms learn through rewards and a process of trial-and-error. This approach is strongly inspired by the study of animal behaviour and has led to outstanding achievements. However, artificial agents still struggle with a number of difficulties, such as learning in changing environments and over longer timescales, states abstractions, generalizing and transferring knowledge. Biological agents, on the other hand, excel at these tasks. The first edition of our workshop last year brought together leading and emerging researchers from Neuroscience, Psychology and Machine Learning to share how neural and cognitive mechanisms can provide insights for RL research and how machine learning advances can further our understanding of brain and behaviour. This year, we want to build on the success of our previous workshop, by expanding on the challenges that emerged and extending to novel perspectives. The problem of state and action representation and abstraction emerged quite strongly last year, so this year’s program aims to add new perspectives like hierarchical reinforcement learning, structure learning and their biological underpinnings. Additionally, we will address learning over long timescales, such as lifelong learning or continual learning, by including views from synaptic plasticity and developmental neuroscience. We are hoping to inspire and further develop connections between biological and artificial reinforcement learning by bringing together experts from all sides and encourage discussions that could help foster novel solutions for both communities.


To ask questions please use rocketchat, available only upon registration and login.


2020-12-12T04:30:00-08:00 - 2020-12-12T04:45:00-08:00
Organizers Opening Remarks
Raymond Chua, Feryal Behbahani, Sara Zannone, Ida Momennejad, Rui Ponte Costa, Blake Richards , Doina Precup
2020-12-12T04:45:00-08:00 - 2020-12-12T04:46:00-08:00
Speaker Introduction: Shakir Mohamed
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T04:46:00-08:00 - 2020-12-12T05:16:00-08:00
Invited Talk #1 Shakir Mohamed : Pain and Machine Learning
Shakir Mohamed
2020-12-12T05:16:00-08:00 - 2020-12-12T05:30:00-08:00
Invited talk 1 QnA: Shakir Mohamed
Shakir Mohamed, Raymond Chua, Feryal Behbahani
2020-12-12T05:30:00-08:00 - 2020-12-12T05:31:00-08:00
Speaker Introduction: Claudia Clopath
Raymond Chua, Sara Zannone, Feryal Behbahani
2020-12-12T05:31:00-08:00 - 2020-12-12T06:01:00-08:00
Invited Talk #2 Claudia Clopath (Live) - Continual learning with different timescales.
Claudia Clopath
2020-12-12T06:01:00-08:00 - 2020-12-12T06:15:00-08:00
Invited Talk #2 QnA - Claudia Clopath (Live)
Claudia Clopath, Raymond Chua, Feryal Behbahani
2020-12-12T06:15:00-08:00 - 2020-12-12T06:16:00-08:00
Speaker Introduction: Contributed talk#1
Raymond Chua, Sara Zannone, Feryal Behbahani
2020-12-12T06:16:00-08:00 - 2020-12-12T06:30:00-08:00
Contributed Talk #1: Learning multi-dimensional rules with probabilistic feedback via value-based serial hypothesis testing
Mingyu Song, Ming Bo Cai, Yael Niv
2020-12-12T06:30:00-08:00 - 2020-12-12T06:31:00-08:00
Speaker Introduction: Contributed talk#2
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T06:31:00-08:00 - 2020-12-12T06:45:00-08:00
Contributed Talk #2: Evaluating Agents Without Rewards
Brendon Matusch, Danijar Hafner, Jimmy Ba
2020-12-12T06:45:00-08:00 - 2020-12-12T07:00:00-08:00
Coffee Break
2020-12-12T07:00:00-08:00 - 2020-12-12T07:01:00-08:00
Speaker Introduction: Kim Stachenfeld
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T07:01:00-08:00 - 2020-12-12T07:31:00-08:00
Invited Talk #3 Kim Stachenfeld : Structure Learning and the Hippocampal-Entorhinal Circuit
Kim Stachenfeld
2020-12-12T07:31:00-08:00 - 2020-12-12T07:45:00-08:00
Invited Talk #3 QnA - Kim Stachenfeld
Kim Stachenfeld, Feryal Behbahani, Raymond Chua
2020-12-12T07:45:00-08:00 - 2020-12-12T07:46:00-08:00
Speaker Introduction: George Konidaris
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T07:46:00-08:00 - 2020-12-12T08:16:00-08:00
Invited Talk #4 George Konidaris - Signal to Symbol (via Skills)
George Konidaris
2020-12-12T08:16:00-08:00 - 2020-12-12T08:30:00-08:00
Invited Talk #4 QnA - George Konidaris
George Konidaris, Raymond Chua, Feryal Behbahani
2020-12-12T08:30:00-08:00 - 2020-12-12T08:45:00-08:00
Coffee Break
2020-12-12T08:45:00-08:00 - 2020-12-12T10:00:00-08:00
Panel Discussions
Grace Lindsay, George Konidaris, Shakir Mohamed, Kim Stachenfeld, Peter Dayan, Yael Niv, Doina Precup, Catherine Hartley, Ishita Dasgupta
2020-12-12T10:00:00-08:00 - 2020-12-12T12:00:00-08:00
Break & Poster Session
2020-12-12T12:00:00-08:00 - 2020-12-12T12:01:00-08:00
Speaker Introduction: Ishita Dasgupta
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T12:01:00-08:00 - 2020-12-12T12:31:00-08:00
Invited Talk #5 Ishita Dasgupta - Embedding structure in data: Progress and challenges for the meta-learning approach
Ishita Dasgupta
2020-12-12T12:31:00-08:00 - 2020-12-12T12:45:00-08:00
Invited Talk #5 QnA - Ishita Dasgupta
Ishita Dasgupta, Feryal Behbahani, Raymond Chua
2020-12-12T12:45:00-08:00 - 2020-12-12T12:46:00-08:00
Speaker Introduction: Catherine Hartley
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T12:46:00-08:00 - 2020-12-12T13:16:00-08:00
Invited Talk #6 Catherine Hartley - Developmental tuning of action selection
Catherine Hartley
2020-12-12T13:16:00-08:00 - 2020-12-12T13:30:00-08:00
Invited Talk #6 QnA - Catherine Hartley
Catherine Hartley, Raymond Chua, Feryal Behbahani
2020-12-12T13:30:00-08:00 - 2020-12-12T13:45:00-08:00
Coffee Break
2020-12-12T13:45:00-08:00 - 2020-12-12T13:46:00-08:00
Speaker Introduction: Contributed talk#3 speaker
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T13:46:00-08:00 - 2020-12-12T14:00:00-08:00
Contributed Talk #3: Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc Bellemare
2020-12-12T14:00:00-08:00 - 2020-12-12T14:01:00-08:00
Speaker Introduction: Yael Niv
Raymond Chua, Feryal Behbahani, Sara Zannone
2020-12-12T14:01:00-08:00 - 2020-12-12T14:31:00-08:00
Invited Talk #7 Yael Niv - Latent causes, prediction errors and the organization of memory
Yael Niv
2020-12-12T14:31:00-08:00 - 2020-12-12T14:45:00-08:00
Invited Talk #7 QnA - Yael Niv
Yael Niv, Raymond Chua, Feryal Behbahani
2020-12-12T14:45:00-08:00 - 2020-12-12T14:55:00-08:00
Closing remarks
Raymond Chua, Feryal Behbahani, Rui Ponte Costa, Doina Precup, Blake Richards , Ida Momennejad
2020-12-12T14:55:00-08:00 - 2020-12-12T15:55:00-08:00
Social & Poster Session