Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning

TL;DR

This paper extends the Hindsight Experience Replay algorithm to handle linearly-weighted multi-objective rewards, enabling a single policy to generalize across all linear combinations of multiple reward functions in deep reinforcement learning.

Contribution

It introduces a novel approach that allows policies to generalize across multiple reward combinations, unlike previous methods focusing only on Q-function generalization.

Findings

The algorithm successfully generalizes across all linear reward combinations.

It enables learning a single policy for multi-objective rewards.

Applicable to continuous action spaces.

Abstract

Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learning algorithm. The advantage is that the algorithm can then use the reward function to check the reward for states that the agent hasn't even encountered yet. In addition, the algorithm can simultaneously learn policies for multiple reward functions. For each state, the algorithm would calculate the reward using each of the reward functions and add the rewards to its experience replay dataset. The Hindsight Experience Replay algorithm developed by Andrychowicz et al. (2017) does just this, and learns to generalize across a distribution of sparse, goal-based rewards. We extend this algorithm to linearly-weighted, multi-objective rewards and learn a single policy that can generalize across all linear combinations of the multi-objective reward. Whereas other multi-objective algorithms teach the Q-function to generalize across the reward weights, our algorithm enables the policy to generalize, and can thus be used with continuous actions.