Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning

12/03/2018
by   Aishwarya Agrawal, et al.
0

Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images of the scenes. A symbolic instruction consistent with the goal images is used as the conditioning input for our policies. Since a single instruction corresponds to a diverse set of different but still consistent end-goal images, the agent needs to learn to generate a distribution over programs given an instruction. We demonstrate that with simple changes to the reinforced adversarial learning objective, we can learn instruction conditioned policies to achieve the corresponding diverse set of goals. Most importantly, our agent's stochastic policy is shown to more accurately capture the diversity in the goal distribution than a fixed pixel-based reward function baseline. We demonstrate the efficacy of our approach on two domains: (1) drawing MNIST digits with a paint software conditioned on instructions and (2) constructing scenes in a 3D editor that satisfies a certain instruction.

READ FULL TEXT
research
06/12/2020

Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL

In the real world, linguistic agents are also embodied agents: they perc...
research
04/11/2021

Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning

It is of significance for an agent to learn a widely applicable and gene...
research
11/28/2018

Unsupervised Control Through Non-Parametric Discriminative Rewards

Learning to control an environment without hand-crafted rewards or exper...
research
06/30/2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Our goal is for robots to follow natural language instructions like "put...
research
03/26/2023

Learning Generative Models with Goal-conditioned Reinforcement Learning

We present a novel, alternative framework for learning generative models...
research
04/13/2023

Language Instructed Reinforcement Learning for Human-AI Coordination

One of the fundamental quests of AI is to produce agents that coordinate...
research
07/12/2019

Navigating an Infinite Space with Unreliable Movements

We consider a search problem on a 2-dimensional infinite grid with a sin...

Please sign up or login with your details

Forgot password? Click here to reset