Timezone: »
The Predictive Information is the mutual information between the past and the future, I(Xpast; Xfuture). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. To test our hypothesis, we train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics using a contrastive version of the Conditional Entropy Bottleneck (CEB) objective. We refer to these as Predictive Information SAC (PI-SAC) agents. We show that PI-SAC agents can substantially improve sample efficiency over challenging baselines on tasks from the DM Control suite of continuous control environments. We evaluate PI-SAC agents by comparing against uncompressed PI-SAC agents, other compressed and uncompressed agents, and SAC agents directly trained from pixels. Our implementation is given on GitHub.
Author Information
Kuang-Huei Lee (Google Brain)
Ian Fischer (Google)
Anthony Liu (University of Michigan)
Yijie Guo (University of Michigan)
Honglak Lee (Google Brain)
John Canny (UC Berkeley)
Sergio Guadarrama (Google Research)
More from the Same Authors
-
2020 Poster: Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards »
Yijie Guo · Jongwook Choi · Marcin Moczulski · Shengyu Feng · Samy Bengio · Mohammad Norouzi · Honglak Lee -
2020 Poster: An Unsupervised Information-Theoretic Perceptual Quality Metric »
Sangnie Bhardwaj · Ian Fischer · Johannes Ballé · Troy Chinen -
2020 Poster: Ode to an ODE »
Krzysztof Choromanski · Jared Quincy Davis · Valerii Likhosherstov · Xingyou Song · Jean-Jacques Slotine · Jacob Varley · Honglak Lee · Adrian Weller · Vikas Sindhwani -
2019 Poster: Unsupervised learning of object structure and dynamics from videos »
Matthias Minderer · Chen Sun · Ruben Villegas · Forrester Cole · Kevin Murphy · Honglak Lee -
2018 Poster: Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion »
Jacob Buckman · Danijar Hafner · George Tucker · Eugene Brevdo · Honglak Lee -
2018 Oral: Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion »
Jacob Buckman · Danijar Hafner · George Tucker · Eugene Brevdo · Honglak Lee -
2018 Poster: GILBO: One Metric to Measure Them All »
Alexander Alemi · Ian Fischer -
2018 Spotlight: GILBO: One Metric to Measure Them All »
Alexander Alemi · Ian Fischer -
2018 Poster: Data-Efficient Hierarchical Reinforcement Learning »
Ofir Nachum · Shixiang (Shane) Gu · Honglak Lee · Sergey Levine -
2018 Poster: Content preserving text generation with attribute controls »
Lajanugen Logeswaran · Honglak Lee · Samy Bengio -
2016 Poster: Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision »
Xinchen Yan · Jimei Yang · Ersin Yumer · Yijie Guo · Honglak Lee