Reading Group

We have a reading group in place that meets every two Friday in the smARTLab.

Date Time Paper
7th August 2020 1pm-2pm One Policy to Control Them All:Shared Modular Policies for Agent-Agnostic Control
17th July 2020 1pm-2pm Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
26th June 2020 1pm-2pm LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood
12th June 2020 1pm-2pm Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters
15th May 2020 1pm-2pm Bounded Seed-AGI
23rd April 2020 1pm-2pm Reinforcement Learning Upside Down: Don’t Predict Rewards — Just Map Them to Actions
Training Agents using Upside-Down Reinforcement Learning
20th March 2020 1pm-2pm See, feel, act: Hierarchical learning for complex manipulation skills with multisensory fusion
28th February 2020 1pm-2pm Compressing Deep Neural Networks via Layer Fusion
24th January 2020 1pm-2pm On the Morality of Artificial Intelligence
22th November 2019 1pm-2pm The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Rethinking the Value of Network Pruning
8th November 2019 1pm-2pm Connecting Generative Adversarial Networks and Actor-Critic Methods
27th September 2019 1pm-2pm On Unifying Deep Generative Models
13th September 2019 1pm-2pm Weight Agnostic Neural Networks
30th August 2019 1pm-2pm Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules
9th August 2019 1pm-2pm World Models
7th July 2019 1pm-2pm Neural Logic Reinforcement Learning
7th June 2019 1pm-2pm Recurrent Value Functions
22nd March 2019 1pm-2pm Backpropagation through time and the brain
1st February 2019 1pm-2pm Neural Ordinary Differential Equations
7th December 2018 1pm-2pm Interactive Perception: Leveraging Action in Perception and Perception in Action
23th November 2018 1pm-2pm Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
16th November 2018 1pm-2pm Learning Robot Tactile Sensing for Object Manipulation
19th October 2018 1pm-2pm Re-evaluating Evaluation
28th September 2018 1pm-2pm Building Machines That Learn and Think Like People
6th July 2018 1pm-2pm Deep Reinforcement Learning that Matters
15th June 2018 1pm-2pm Observe and Look Further: Achieving Consistent Performance on Atari
1st June 2018 1pm-2pm Learning Explanatory Rules from Noisy Data
11th May 2018 1pm-2pm Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
23rd Mar 2018 1pm-2pm The Option-Critic Architecture
9th Mar 2018 1pm-2pm Reinforcement Learning Neural Turing Machines
23rd Feb 2018 1pm-2pm Efficient behavior learning in human–robot collaboration
26th Jan 2018 11am-12pm Robust and Efficient Transfer Learning with Hidden
Parameter Markov Decision Processes
15th Dec 2017 11am-12pm Posterior Sampling for Large Scale Reinforcement Learning
8th Dec 2017 12pm-1pm A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
17th Nov 2017 12pm-1pm Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards