Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

by   Qinqing Zheng, et al.

Natural agents can effectively learn from multiple data sources that differ in size, quality, and types of measurements. We study this heterogeneity in the context of offline reinforcement learning (RL) by introducing a new, practically motivated semi-supervised setting. Here, an agent has access to two sets of trajectories: labelled trajectories containing state, action, reward triplets at every timestep, along with unlabelled trajectories that contain only state and reward information. For this setting, we develop a simple meta-algorithmic pipeline that learns an inverse-dynamics model on the labelled data to obtain proxy-labels for the unlabelled data, followed by the use of any offline RL algorithm on the true and proxy-labelled trajectories. Empirically, we find this simple pipeline to be highly successful – on several D4RL benchmarks <cit.>, certain offline RL algorithms can match the performance of variants trained on a fully labeled dataset even when we label only 10% trajectories from the low return regime. Finally, we perform a large-scale controlled empirical study investigating the interplay of data-centric properties of the labelled and unlabelled datasets, with algorithmic design choices (e.g., inverse dynamics, offline RL algorithm) to identify general trends and best practices for training RL agents on semi-supervised offline datasets.


page 1

page 2

page 3

page 4


Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning

Recent progress in deep learning has relied on access to large and diver...

Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments

One of the key challenges of Reinforcement Learning (RL) is the ability ...

The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning

Self-supervised methods have become crucial for advancing deep learning ...

Survival Instinct in Offline Reinforcement Learning

We present a novel observation about the behavior of offline reinforceme...

State Advantage Weighting for Offline RL

We present state advantage weighting for offline reinforcement learning ...

Offline Reinforcement Learning at Multiple Frequencies

Leveraging many sources of offline robot data requires grappling with th...

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Learning to control an agent from data collected offline in a rich pixel...

Please sign up or login with your details

Forgot password? Click here to reset