Reinforcement Learning at QMUL
Research Interest
Learning, inference and behaviour in the perception-action loop with a specific interest in model-based RL, sparse rewards problems and action advising.
Reading Group
Welcome to the Reinforcement Learning reading group at the Queen Mary University of London.
| Date | Paper | Presenter |
|---|---|---|
| 4 February 2020 | Empowerment-driven Exploration using Mutual Information Estimation - Kumar (2018) | Alvaro Ovalle & Martin Balla |
| 28 January 2020 | MINE: Mutual Information Neural Estimation - Belghazi et al. (2018) | Alvaro Ovalle & Martin Balla |
| 14 January 2020 | The Journey is the Reward: Unsupervised Learning of Influential Trajectories - Binas et al. (2019) | Alvaro Ovalle & Martin Balla |
| 8 January 2020 | Empowerment – an introduction - Salge et al. (2013) | Alvaro Ovalle & Martin Balla |
| 21 November 2019 | QXplore: Q-learning Exploration by Maximizing Temporal Difference Error - Simmons-Edler et al. (2019) | Ercüment İlhan |
| 7 November 2019 | Grandmaster level in StarCraft II using multi-agent reinforcement learning - Vinyals et al. (2019) | Martin Balla |
| 31 October 2019 | Unsupervised Video Object Segmentation for Deep Reinforcement Learning - Goel et al. (2018) | Alvaro Ovalle |
| 24 October 2019 | Solving Rubik’s Cube with a Robot Hand - OpenAI et al. (2019) | Chris Bamford |
| 17 October 2019 | Diversity is all you need - Eysenbach et al. (2018) | Martin Balla |
| 09 October 2019 | Deep Exploration via Bootstrapped DQN - Osband et al. (2016) | Ercüment İlhan |
| 28 August 2019 | Learning Latent Dynamics for Planning from Pixels - Hafner et al. (2018) | Alvaro Ovalle |
| 16 August 2019 | Shaping belief states with generative environment models for RL - Gregor et al. (2019) | Chris Bamford |
| 4 July 2019 | Learning to act by predicting the future - Dosovitskiy & Koltun (2016) | Martin Balla |
| 27 June 2019 | Imitating latent policies from observation - Edwards et al. (2018) | Ercüment İlhan |
| 1 May 2019 | World Discovery Models - Azar et al. (2019) | Alvaro Ovalle |
| 17 April 2019 | Provably efficient RL with Rich Observations via Latent State Decoding - Du et al. (2019) | Chris Bamford |
| 10 April 2019 | Distilling Policy Distillation - Czarnecki et al. (2019) | Martin Balla |
| 3 April 2019 | Deep Reinforcement Learning that Matter - Henderson et al. (2017) | Ercüment İlhan |
| 21 March 2019 | Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play - Sukhbaatar et al. (2017) | Alvaro Ovalle |
| 6 March 2019 | Deep reinforcement learning with relational inductive biases - Zambaldi et al. (2018) | Martin Balla |
| 28 Feb 2019 | Show, Attend and Tell: Neural Image Caption Generation with Visual Attention - Xu et al. (2015) | Chris Bamford |
| 13 Feb 2019 | Universal Value Function Approximators - Schaul et al. (2015) | Ercüment İlhan |
| 6 Feb 2019 | Temporal Difference Variational Auto-Encoder - Gregor et al. (2018) | Alvaro Ovalle & Chris Bamford |
| 6 Feb 2019 | An investigation of model-free planning - Guez et al. (2019) | Alvaro Ovalle |
| 30 Jan 2019 | Hindsight Experience Replay - Andrychowicz et al. (2017) | Alvaro Ovalle |
| 24 Jan 2019 | Strategic Attentive Writer for Learning Macro-Actions - Vezhnevets et al. (2016) | Martin Balla |
| 16 Jan 2019 | Imagination-Augmented Agents for Deep Reinforcement Learning - Weber et al. (2017) | Chris Bamford |
| 12 Dec 2018 | Machine Theory of Mind - Rabinowitz et al. (2018) | Ercüment İlhan |
| 15 Nov 2018 | Exploration by Random Network Distillation - Burda et al. (2018) | Alvaro Ovalle |
The end is nigh