Workshop
Biological and Artificial Reinforcement Learning
Raymond Chua · Feryal Behbahani · Julie J Lee · Sara Zannone · Rui Ponte Costa · Blake Richards · Ida Momennejad · Doina Precup
Sat 12 Dec, 4:30 a.m. PST
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.
Schedule
Sat 4:30 a.m. - 4:45 a.m.
|
Organizers Opening Remarks
(
Live Intro
)
>
|
Raymond Chua · Feryal Behbahani · Julie J Lee · Ida Momennejad · Rui Ponte Costa · Blake Richards · Doina Precup 🔗 |
Sat 4:45 a.m. - 4:46 a.m.
|
Speaker Introduction: Shakir Mohamed
(
Live Intro
)
>
|
Feryal Behbahani · Raymond Chua 🔗 |
Sat 4:46 a.m. - 5:16 a.m.
|
Invited Talk #1 Shakir Mohamed : Pain and Machine Learning
(
Invited Talk
)
>
SlidesLive Video |
Shakir Mohamed 🔗 |
Sat 5:16 a.m. - 5:30 a.m.
|
Invited talk 1 QnA: Shakir Mohamed
(
Live QnA
)
>
|
Shakir Mohamed · Feryal Behbahani · Raymond Chua 🔗 |
Sat 5:30 a.m. - 5:31 a.m.
|
Speaker Introduction: Claudia Clopath
(
Live Intro
)
>
|
Raymond Chua · Feryal Behbahani · Rui Ponte Costa 🔗 |
Sat 5:31 a.m. - 6:01 a.m.
|
Invited Talk #2 Claudia Clopath (Live, no recording) - Continual learning with different timescales.
(
Invited Live Talk
)
>
|
Claudia Clopath 🔗 |
Sat 6:01 a.m. - 6:15 a.m.
|
Invited Talk #2 QnA - Claudia Clopath (Live, no recording)
(
Live QnA
)
>
|
Claudia Clopath · Rui Ponte Costa · Raymond Chua · Feryal Behbahani 🔗 |
Sat 6:15 a.m. - 6:16 a.m.
|
Speaker Introduction: Contributed talk#1
(
Live Intro
)
>
|
Raymond Chua · Feryal Behbahani 🔗 |
Sat 6:16 a.m. - 6:30 a.m.
|
Contributed Talk #1: Learning multi-dimensional rules with probabilistic feedback via value-based serial hypothesis testing
(
Contributed Talk
)
>
SlidesLive Video |
Mingyu Song · Ming Bo Cai · Yael Niv 🔗 |
Sat 6:30 a.m. - 6:31 a.m.
|
Speaker Introduction: Contributed talk#2
(
Live Intro
)
>
|
Raymond Chua · Feryal Behbahani · Sara Zannone 🔗 |
Sat 6:31 a.m. - 6:45 a.m.
|
Contributed Talk #2: Evaluating Agents Without Rewards
(
Contributed Talk
)
>
|
Brendon Matusch · Danijar Hafner · Jimmy Ba 🔗 |
Sat 6:45 a.m. - 7:00 a.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗 |
Sat 7:00 a.m. - 7:01 a.m.
|
Speaker Introduction: Kim Stachenfeld
(
Live Intro
)
>
|
Ida Momennejad · Raymond Chua · Feryal Behbahani 🔗 |
Sat 7:01 a.m. - 7:31 a.m.
|
Invited Talk #3 Kim Stachenfeld : Structure Learning and the Hippocampal-Entorhinal Circuit
(
Invited Talk
)
>
SlidesLive Video |
Kimberly Stachenfeld 🔗 |
Sat 7:31 a.m. - 7:45 a.m.
|
Invited Talk #3 QnA - Kim Stachenfeld
(
Live QnA
)
>
|
Kimberly Stachenfeld · Ida Momennejad · Feryal Behbahani · Raymond Chua 🔗 |
Sat 7:45 a.m. - 7:46 a.m.
|
Speaker Introduction: George Konidaris
(
Live Intro
)
>
|
Raymond Chua · Feryal Behbahani 🔗 |
Sat 7:46 a.m. - 8:16 a.m.
|
Invited Talk #4 George Konidaris - Signal to Symbol (via Skills)
(
Invited Talk
)
>
SlidesLive Video |
George Konidaris 🔗 |
Sat 8:16 a.m. - 8:30 a.m.
|
Invited Talk #4 QnA - George Konidaris
(
Live QnA
)
>
|
George Konidaris · Raymond Chua · Feryal Behbahani 🔗 |
Sat 8:30 a.m. - 8:45 a.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗 |
Sat 8:45 a.m. - 10:00 a.m.
|
Panel Discussions
(
Panel Discussions
)
>
|
Grace Lindsay · George Konidaris · Shakir Mohamed · Kimberly Stachenfeld · Peter Dayan · Yael Niv · Doina Precup · Catherine Hartley · Ishita Dasgupta 🔗 |
Sat 10:00 a.m. - 12:00 p.m.
|
Break & Poster Session on Gather.Town (Main) ( Poster Session ) > link | 🔗 |
Sat 12:00 p.m. - 12:01 p.m.
|
Speaker Introduction: Ishita Dasgupta
(
Live Intro
)
>
|
Julie J Lee · Raymond Chua · Feryal Behbahani 🔗 |
Sat 12:01 p.m. - 12:31 p.m.
|
Invited Talk #5 Ishita Dasgupta - Embedding structure in data: Progress and challenges for the meta-learning approach
(
Invited Talk
)
>
SlidesLive Video |
Ishita Dasgupta 🔗 |
Sat 12:31 p.m. - 12:45 p.m.
|
Invited Talk #5 QnA - Ishita Dasgupta
(
Live QnA
)
>
|
Ishita Dasgupta · Julie J Lee · Feryal Behbahani · Raymond Chua 🔗 |
Sat 12:45 p.m. - 12:46 p.m.
|
Speaker Introduction: Catherine Hartley
(
Live Intro
)
>
|
Julie J Lee · Raymond Chua · Feryal Behbahani 🔗 |
Sat 12:46 p.m. - 1:16 p.m.
|
Invited Talk #6 Catherine Hartley - Developmental tuning of action selection
(
Invited Talk
)
>
SlidesLive Video |
Catherine Hartley 🔗 |
Sat 1:16 p.m. - 1:30 p.m.
|
Invited Talk #6 QnA - Catherine Hartley
(
Live QnA
)
>
|
Catherine Hartley · Julie J Lee · Raymond Chua · Feryal Behbahani 🔗 |
Sat 1:30 p.m. - 1:45 p.m.
|
Coffee Break
|
🔗 |
Sat 1:45 p.m. - 1:46 p.m.
|
Speaker Introduction: Contributed talk#3 speaker
(
Live Intro
)
>
|
Feryal Behbahani · Raymond Chua 🔗 |
Sat 1:46 p.m. - 2:00 p.m.
|
Contributed Talk #3: Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
(
Contributed Talk
)
>
|
Rishabh Agarwal · Marlos C. Machado · Pablo Samuel Castro · Marc Bellemare 🔗 |
Sat 2:00 p.m. - 2:01 p.m.
|
Speaker Introduction: Yael Niv
(
Live Intro
)
>
|
Doina Precup · Raymond Chua · Feryal Behbahani 🔗 |
Sat 2:01 p.m. - 2:31 p.m.
|
Invited Talk #7 Yael Niv - Latent causes, prediction errors and the organization of memory
(
Invited Talk
)
>
SlidesLive Video |
Yael Niv 🔗 |
Sat 2:31 p.m. - 2:45 p.m.
|
Invited Talk #7 QnA - Yael Niv
(
Live QnA
)
>
|
Yael Niv · Doina Precup · Raymond Chua · Feryal Behbahani 🔗 |
Sat 2:45 p.m. - 2:55 p.m.
|
Closing remarks
(
Live Closing remarks
)
>
|
Raymond Chua · Feryal Behbahani · Julie J Lee · Rui Ponte Costa · Doina Precup · Blake Richards · Ida Momennejad 🔗 |
Sat 2:55 p.m. - 3:55 p.m.
|
Social & Poster Session on Gather.Town ( Poster Session ) > link | 🔗 |