Skip to main content
9 votes
Accepted

Why is the reward in reinforcement learning always a scalar?

If you have multiple types of rewards (say, R1 and R2), then it is no longer clear what would be the optimal way to act: it can happen that one way of acting would maximize R1 and another way would ...
present's user avatar
  • 241
8 votes

Why is the reward in reinforcement learning always a scalar?

Rather than the survey by Liu et al. recommended above, I'd suggest you read the following survey paper for an overview of MORL (disclaimer - I was a co-author on this, but I genuinely think it is a ...
Peter Vamplew's user avatar
7 votes

Why is the reward in reinforcement learning always a scalar?

Markov decision problems are usually defined with a reward function $r:\mathcal{S}\times\mathcal{A}\rightarrow\mathbb{R}$, and in these cases the rewards are expected to be scalar real values. This ...
Hai Nguyen's user avatar
5 votes
Accepted

Can rewards be decomposed into components?

If I understood correctly you're looking at a Multi-Objective Reinforcement Learning (MORL). Keep in mind however that many scientist will often follow the reward hypothesis (Sutton and Barto) which ...
Tomasz Bartkowiak's user avatar
4 votes

What are some simple open problems in multi-agent RL that would be suited for a bachelor's thesis?

I have several undergraduates working on multiagent deep RL problems for their theses, but most of them have been working for 8-9 months. 2 might be a stretch. Good multiagent deep RL problems for a ...
John Doucette's user avatar
3 votes
Accepted

Can the rewards be matrices when using DQN?

Generally speaking, is it better for rewards to be a scalar, or is using matrices okay? Rewards need to be scalar, real values to match to standard theory of Markov decision processes (MDPs) and ...
Neil Slater's user avatar
  • 32.1k
3 votes

What are preferences and preference functions in multi-objective reinforcement learning?

In MORL the reward component is a vector rather than a scalar, with an element for each objective. So if we are using a multiobjective version of an algorithm like Q-learning, the Q-values stored for ...
Peter Vamplew's user avatar
2 votes

Can rewards be decomposed into components?

I agree with Tomasz that the approach you are describing falls within the field of MORL. For a solid introduction MORL I would recommend the survey by Roijers, D. M., Vamplew, P., Whiteson, S., & ...
Peter Vamplew's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible