paper-with-me

Papers

DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction

2024-06-30 · Ameya Pore, Riccardo Muradore, Diego Dall'Alba

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the agent's knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations (DEAR), that uses the segmentation mask of the agent as supervision to learn disentangled representations of the environment and the agent through feature separation constraints. Unlike previous approaches, DEAR does not require reconstruction of visual observations. These representations are then used as an auxiliary loss to the RL objective, encouraging the agent to focus on the relevant features of the environment. We evaluate DEAR on two challenging benchmarks: Distracting DeepMind control suite and Franka Kitchen manipulation tasks. Our findings demonstrate that DEAR surpasses state-of-the-art methods in sample efficiency, achieving comparable or superior performance with reduced parameters. Our results indicate that integrating agent knowledge into visual RL methods has the potential to enhance their learning efficiency and robustness.

📄 PDF Abstract BibTeX arXiv:2407.00633

Code (1)

ameyapores/dear 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

2023-05-23 · NeurIPS 2023 11 · Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna 외

Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these…

continuous-controlContinuous ControlDisentanglementreinforcement-learning+2

Weakly Supervised Disentangled Generative Causal Representation Learning

2020-10-06 · Xinwei Shen, Furui Liu, Hanze Dong, Qing Lian 외

This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information. Unlike existing disentanglement methods that enforce independence of the latent variabl…

DisentanglementRepresentation Learning

Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning

2022-02-28 · Zhifeng Qian, Mingyu You, Hongjun Zhou, Bin He

Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically r…

Positionreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning

2022-07-12 · Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna 외

Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training. This issue is especially problematic for image-based RL, where a…

Disentanglementreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Zero-Shot Policy Transfer with Disentangled Attention

2019-09-25 · Josh Roy, George Konidaris

Domain adaptation is an open problem in deep reinforcement learning (RL). Often, agents are asked to perform in environments where data is difficult to obtain. In such settings, agents are trained in similar environments…

Deep Reinforcement LearningDomain AdaptationReinforcement Learning (RL)Representation Learning