DeepAI AI Chat
Log In Sign Up

Provable Benefits of Representational Transfer in Reinforcement Learning

05/29/2022
by   Alekh Agarwal, et al.
7

We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a target task. We propose a new notion of task relatedness between source and target tasks, and develop a novel approach for representational transfer under this assumption. Concretely, we show that given generative access to source tasks, we can discover a representation, using which subsequent linear RL techniques quickly converge to a near-optimal policy, with only online access to the target task. The sample complexity is close to knowing the ground truth features in the target task, and comparable to prior representation learning results in the source tasks. We complement our positive results with lower bounds without generative access, and validate our findings with empirical evaluation on rich observation MDPs that require deep exploration.

READ FULL TEXT
01/22/2018

Cross-Domain Transfer in Reinforcement Learning using Target Apprentice

In this paper, we present a new approach to Transfer Learning (TL) in Re...
08/31/2011

Transfer from Multiple MDPs

Transfer reinforcement learning (RL) methods leverage on the experience ...
12/14/2020

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

Several practical applications of reinforcement learning involve an agen...
06/13/2022

Provable Benefit of Multitask Representation Learning in Reinforcement Learning

As representation learning becomes a powerful technique to reduce sample...
01/01/2022

Transfer RL across Observation Feature Spaces via Model-Based Regularization

In many reinforcement learning (RL) applications, the observation space ...
06/20/2020

On the Theory of Transfer Learning: The Importance of Task Diversity

We provide new statistical guarantees for transfer learning via represen...
05/12/2018

Adversarial Task Transfer from Preference

Task transfer is extremely important for reinforcement learning, since i...