Exploration for Multi-task Reinforcement Learning with Deep Generative Models

by   Sai Praveen Bangaru, et al.
Indian Institute Of Technology, Madras

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as E^3, R_max, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We evaluate our method on a new set of environments and provide intuitive interpretation of our results.


page 5

page 6

page 8


Exploration and Incentives in Reinforcement Learning

How do you incentivize self-interested agents to explore when they prefe...

TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL

Transferring knowledge among various environments is important to effici...

Individual specialization in multi-task environments with multiagent reinforcement learners

There is a growing interest in Multi-Agent Reinforcement Learning (MARL)...

Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework

In this work, we investigate the potential of improving multi-task train...

A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning

In this paper we consider the problem of how a reinforcement learning ag...

A Memory-Related Multi-Task Method Based on Task-Agnostic Exploration

We pose a new question: Can agents learn how to combine actions from pre...

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition

Representation learning and exploration are among the key challenges for...

Please sign up or login with your details

Forgot password? Click here to reset