Playlist: 25 videos

Deep Reinforcement Learning

0:37:44

MOPO: Model-Based Offline Policy Optimization

Tengyu Ma (Stanford
https://simons.berkeley.edu/talks/tbd-206
Deep Reinforcement Learning
Visit talk page
0:27:46

Learning from the Past Without Great Exploration

Emma Brunskill (Stanford)
https://simons.berkeley.edu/talks/tbd-215
Deep Reinforcement Learning
Visit talk page
0:32:1

Offline Deep Reinforcement Learning Algorithms

Sergey Levine (UC Berkeley)
https://simons.berkeley.edu/talks/tbd-216
Deep Reinforcement Learning
Visit talk page
0:32:11

Attacking the Off-Policy Problem With Duality

Ofir Nachum (Google Research)
https://simons.berkeley.edu/talks/tbd-221
Deep Reinforcement Learning
Visit talk page
0:40:1

Discussion: Offline Reinforcement Learning

Moderator: Pablo Castro (Google)
https://simons.berkeley.edu/talks/tbd-230
Deep Reinforcement Learning
Visit talk page
0:31:22

Behaviour Suite for Reinforcement Learning

Ian Osband (DeepMind)
https://simons.berkeley.edu/talks/tbd-207
Deep Reinforcement Learning
Visit talk page
0:31:22

Learning Exploration Strategies with Meta-Reinforcement Learning

Chelsea Finn (Stanford University)
https://simons.berkeley.edu/talks/tbd-214
Deep Reinforcement Learning
Visit talk page
0:30:38

Temporally-Extended ε-Greedy Exploration

Will Dabney (DeepMind)
https://simons.berkeley.edu/talks/tbd-217
Deep Reinforcement Learning
Visit talk page
0:30:56

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

Alekh Agarwal (Microsoft Research)
https://simons.berkeley.edu/talks/tbd-222
Deep Reinforcement Learning
Visit talk page
0:37:40

Discussion: Exploration

Moderator: Joel Lehman (Uber)
https://simons.berkeley.edu/talks/tbd-229
Deep Reinforcement Learning
Visit talk page