Elise van der Pol
List is open to suggestions/changes. To join the reading group, please subscribe.

Planned Sessions

Date/Time Paper Authors Location Discussant
31st March 2017,
12:00 - 13:00
Bridging the Gap Between Value and Policy Based Reinforcement Learning Nachum et al. C2.111 Chiel Kooijman

Past Sessions

Date/Time Paper Authors Location Discussant
24th March 2017,
11:00 - 13:00
Increasing the Action Gap: New Operators for Reinforcement Learning Bellemare et al. C3.265 Luisa Zintgraf
10th March 2017,
11:00 - 13:00
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
Learning Multiagent Communication with Backpropagation
Leibo et al.
Sukhbataar et al.
C3.265 Elise van der Pol
Jaimy van Dijk
24th February 2017,
11:00 - 13:00
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
Generative Adversarial Imitation Learning
Finn et al.
Ho et al.
C3.265 Auke Wiggers
Kyriacos Shiarlis
10th February 2017,
11:00 - 13:00
RL²: Fast Reinforcement Learning via Slow Reinforcement Learning
Learning to Reinforcement Learn
Duan et al.
Wang et al.
C3.265 Luisa Zintgraf
Chiel Kooijman
27th January 2017,
11:00 - 13:00
Deep Recurrent Q-learning for Partially Observable MDPs
Trust Region Policy Optimization
Hausknecht et al.
Schulman et al.
C3.265 Jaimy van Dijk
Joost van Doorn
13th January 2017,
11:00 - 13:00
Continuous Control with Deep Reinforcement Learning
Connecting Generative Adversarial Networks and Actor-Critic Methods
Lillicrap et al.
Pfau et al.
C3.265 Tycho van der Ouderaa
Elise van der Pol
16th December 2016,
11:00 - 12:00
Deep Exploration via Bootstrapped DQN Osband et al. C3.265 Diederik Roijers
2nd December 2016,
11:00 - 12:00
Dueling Network Architectures for Deep Reinforcement Learning Wang et al. C3.265 Luisa Zintgraf
18th November 2016,
11:00 - 12:00
Prioritized Experience Replay
Deep Reinforcement Learning with Double Q-learning
Schaul et al.
Van Hasselt et al.
A1.12 Chiel Kooijman
Elise van der Pol
4th November 2016,
11:00 - 12:00
Human-level Control through Deep Reinforcement Learning Mnih et al. C2.111