Unbiased Methods for Multi-Goal Reinforcement Learning

by   Léonard Blier, et al.

In multi-goal reinforcement learning (RL) settings, the reward for each goal is sparse, and located in a small neighborhood of the goal. In large dimension, the probability of reaching a reward vanishes and the agent receives little learning signal. Methods such as Hindsight Experience Replay (HER) tackle this issue by also learning from realized but unplanned-for goals. But HER is known to introduce bias, and can converge to low-return policies by overestimating chancy outcomes. First, we vindicate HER by proving that it is actually unbiased in deterministic environments, such as many optimal control settings. Next, for stochastic environments in continuous spaces, we tackle sparse rewards by directly taking the infinitely sparse reward limit. We fully formalize the problem of multi-goal RL with infinitely sparse Dirac rewards at each goal. We introduce unbiased deep Q-learning and actor-critic algorithms that can handle such infinitely sparse rewards, and test them in toy environments.



There are no comments yet.


page 1

page 2

page 3

page 4


SIBRE: Self Improvement Based REwards for Reinforcement Learning

We propose a generic reward shaping approach for improving rate of conve...

Effects of sparse rewards of different magnitudes in the speed of learning of model-based actor critic methods

Actor critic methods with sparse rewards in model-based deep reinforceme...

The problem with DDPG: understanding failures in deterministic environments with sparse rewards

In environments with continuous state and action spaces, state-of-the-ar...

Reward prediction for representation learning and reward shaping

One of the fundamental challenges in reinforcement learning (RL) is the ...

Episodic Curiosity through Reachability

Rewards are sparse in the real world and most today's reinforcement lear...

Reinforcement Learning with Perturbed Rewards

Recent studies have shown the vulnerability of reinforcement learning (R...

Can Q-learning solve Multi Armed Bantids?

When a reinforcement learning (RL) method has to decide between several ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.