Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

04/30/2020
by   Daniel Guo, et al.
0

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks. Here we introduce Prediction of Bootstrap Latents (PBL), a simple and flexible self-supervised representation learning algorithm for multitask deep RL. PBL builds on multistep predictive representations of future observations, and focuses on capturing structured information about environment dynamics. Specifically, PBL trains its representation by predicting latent embeddings of future observations. These latent embeddings are themselves trained to be predictive of the aforementioned representations. These predictions form a bootstrapping effect, allowing the agent to learn more about the key aspects of the environment dynamics. In addition, by defining prediction tasks completely in latent space, PBL provides the flexibility of using multimodal observations involving pixel images, language instructions, rewards and more. We show in our experiments that PBL delivers across-the-board improved performance over state of the art deep RL agents in the DMLab-30 and Atari-57 multitask setting.

READ FULL TEXT
research
01/28/2022

Mask-based Latent Reconstruction for Reinforcement Learning

For deep reinforcement learning (RL) from pixels, learning effective sta...
research
12/06/2022

Understanding Self-Predictive Learning for Reinforcement Learning

We study the learning dynamics of self-predictive learning for reinforce...
research
05/01/2023

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Representation learning and exploration are among the key challenges for...
research
07/12/2020

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

While deep reinforcement learning excels at solving tasks where large am...
research
08/25/2019

Dynamics-aware Embeddings

In this paper we consider self-supervised representation learning to imp...
research
06/12/2020

Deep Reinforcement and InfoMax Learning

Our work is based on the hypothesis that a model-free agent whose repres...
research
10/19/2022

Palm up: Playing in the Latent Manifold for Unsupervised Pretraining

Large and diverse datasets have been the cornerstones of many impressive...

Please sign up or login with your details

Forgot password? Click here to reset