On Inductive Biases in Deep Reinforcement Learning
Many deep reinforcement learning algorithms contain inductive biases that sculpt the agent's objective and its interface to the environment. These inductive biases can take many forms, including domain knowledge and pretuned hyper-parameters. In general, there is a trade-off between generality and performance when algorithms use such biases. Stronger biases can lead to faster learning, but weaker biases can potentially lead to more general algorithms. This trade-off is important because inductive biases are not free; substantial effort may be required to obtain relevant domain knowledge or to tune hyper-parameters effectively. In this paper, we re-examine several domain-specific components that bias the objective and the environmental interface of common deep reinforcement learning agents. We investigated whether the performance deteriorates when these components are replaced with adaptive solutions from the literature. In our experiments, performance sometimes decreased with the adaptive components, as one might expect when comparing to components crafted for the domain, but sometimes the adaptive components performed better. We investigated the main benefit of having fewer domain-specific components, by comparing the learning performance of the two systems on a different set of continuous control problems, without additional tuning of either system. As hypothesized, the system with adaptive components performed better on many of the new tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning
Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve genera…
reinforcement-learningReinforcement Learning (RL)Biases for Emergent Communication in Multi-agent Reinforcement Learning
We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has …
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply …
MuJoCoUsing Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning ma…
Meta-LearningMeta Reinforcement LearningProgram inductionReinforcement Learning (RL)Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing …
Reinforcement Learning