Adaptive Symmetric Reward Noising for Reinforcement Learning

05/24/2019
by   Refael Vivanti, et al.
0

Recent reinforcement learning algorithms, though achieving impressive results in various fields, suffer from brittle training effects such as regression in results and high sensitivity to initialization and parameters. We claim that some of the brittleness stems from variance differences, i.e. when different environment areas - states and/or actions - have different rewards variance. This causes two problems: First, the "Boring Areas Trap" in algorithms such as Q-learning, where moving between areas depends on the current area variance, and getting out of a boring area is hard due to its low variance. Second, the "Manipulative Consultant" problem, when value-estimation functions used in DQN and Actor-Critic algorithms influence the agent to prefer boring areas, regardless of the mean rewards return, as they maximize estimation precision rather than rewards. This sheds a new light on how exploration contribute to training, as it helps with both challenges. Cognitive experiments in humans showed that noised reward signals may paradoxically improve performance. We explain this using the two mentioned problems, claiming that both humans and algorithms may share similar challenges. Inspired by this result, we propose the Adaptive Symmetric Reward Noising (ASRN), by which we mean adding Gaussian noise to rewards according to their states' estimated variance, thus avoiding the two problems while not affecting the environment's mean rewards behavior. We conduct our experiments in a Multi Armed Bandit problem with variance differences. We demonstrate that a Q-learning algorithm shows the brittleness effect in this problem, and that the ASRN scheme can dramatically improve the results. We show that ASRN helps a DQN algorithm training process reach better results in an end to end autonomous driving task using the AirSim driving simulator.

READ FULL TEXT
research
10/21/2021

Can Q-learning solve Multi Armed Bantids?

When a reinforcement learning (RL) method has to decide between several ...
research
05/09/2018

Reward Estimation for Variance Reduction in Deep Reinforcement Learning

In reinforcement learning (RL), stochastic environments can make learnin...
research
01/18/2020

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...
research
02/12/2021

Disturbing Reinforcement Learning Agents with Corrupted Rewards

Reinforcement Learning (RL) algorithms have led to recent successes in s...
research
04/25/2023

Communication-Constrained Bandits under Additive Gaussian Noise

We study a distributed stochastic multi-armed bandit where a client supp...
research
02/21/2021

Delayed Rewards Calibration via Reward Empirical Sufficiency

Appropriate credit assignment for delay rewards is a fundamental challen...

Please sign up or login with your details

Forgot password? Click here to reset