Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning

Abstract

Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learning yet even a tiny adjustment on them is expensive to evaluate due to the drastically increasing cost of training. To this end, we propose a hindsight reward tweaking approach by designing a novel paradigm for deep reinforcement learning to model the influences of reward functions within a near-optimal space. We simply extend the input observation with a condition vector linearly correlated with the effective environment reward parameters and train the model in a conventional manner except for randomizing reward configurations, obtaining a hyper-policy whose characteristics are sensitively regulated over the condition space. We demonstrate the feasibility of this approach and study one of its potential application in policy performance boosting with multiple MuJoCo tasks.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Continuous control with deep reinforcement learning
• Conditional Generative Adversarial Nets
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to reinforcement learn
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Diversity is All You Need: Learning Skills without a Reward Function
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Learning to Understand Goal Specifications by Modelling Reward
• Semi-supervised Conditional GANs