paper-with-me

홈 › Papers

Diversity Progress for Goal Selection in Discriminability-Motivated RL

2024-11-03 · Erik M. Lintunen, Nadia M. Ady, Christian Guckelsberger

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: "Diversity Progress" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward can motivate the agent to learn a set of diverse skills without extrinsic rewards. We demonstrate empirically that a DP-motivated agent can learn a set of distinguishable skills faster than previous approaches, and do so without suffering from a collapse of the goal distribution -- a known issue with some prior approaches. We end with plans to take this proof-of-concept forward.

📄 PDF Abstract BibTeX arXiv:2411.01521

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

2018-10-15 · Cédric Colas, Pierre Fournier, Olivier Sigaud, Mohamed Chetouani 외

In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a large diversity of goals, aiming to disco…

DiversityEfficient ExplorationMulti-Goal Reinforcement Learningreinforcement-learning+2

Tracking Emotions: Intrinsic Motivation Grounded on Multi-Level Prediction Error Dynamics

2020-07-29 · Guido Schillaci, Alejandra Ciria, Bruno Lara

How do cognitive agents decide what is the relevant information to learn and how goals are selected to gain this knowledge? Cognitive agents need to be motivated to perform any action. We discuss that emotions arise when…

Prediction

Curiosity Driven Exploration of Learned Disentangled Goal Spaces

2018-07-04 · Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer

Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to r…

DiversityEfficient ExplorationRepresentation Learning

Progressive growing of self-organized hierarchical representations for exploration

2020-05-13 · Mayalen Etcheverry, Pierre-Yves Oudeyer, Chris Reinke

Designing agent that can autonomously discover and learn a diversity of structures and skills in unknown changing environments is key for lifelong machine learning. A central challenge is how to learn incrementally repre…

DiversityRepresentation Learning

Discriminative Radial Domain Adaptation

2023-01-01 · Zenan Huang, Jun Wen, Siheng Chen, Linchao Zhu 외

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature…

Domain AdaptationDomain GeneralizationUnsupervised Domain Adaptation