Self-adapting Goals Allow Transfer Of Predictive Models To New Tasks

Abstract

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning architecture which learns a predictive model of the environment that aims to predict only the value of a few key measurements, which are be indicative of an agent's performance. Predicting only a few measurements rather than the entire future state of an environment makes it more feasible to learn a valuable predictive model. We extend this predictive model with a small, evolving neural network that s

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyellefsen2019self

Related papers

• Partial Models For Building Adaptive Model-based Reinforcement Learning Agents (2024)0.00
• Self-supervised Reinforcement Learning That Transfers Using Random Features (2023)2.26
• Unsupervised Predictive Memory In A Goal-directed Agent (2018)0.00
• Adarl: What, Where, And How To Adapt In Transfer Reinforcement Learning (2021)0.00
• Contextual Pre-planning On Reward Machine Abstractions For Enhanced Transfer In Deep Reinforcement Learning (2023)2.26
• Efficient Meta Reinforcement Learning For Preference-based Fast Adaptation (2022)0.00
• Learning To Predict Without Looking Ahead: World Models Without Forward Prediction (2019)0.00
• Deep Online Learning Via Meta-learning: Continual Adaptation For Model-based RL (2018)0.00