Data to 7 Oct 2026

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

arXiv 2005.06800 ↗First posted 14 May 2020cs.LG stat.MLcited by 95

Not on the map. Why?

Abstract (arXiv)

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. To tackle this problem, we decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 22; 2023: 17; 2024: 19; 2025: 21; 2026: 7.

95 papers.

Sort:

By area:

2021Dropout Q-Functions for Doubly Efficient Reinforcement Learningcited by 108
2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 102
2022A Survey on Model-based Reinforcement Learningcited by 65
2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 49
2021Offline Reinforcement Learning with Reverse Model-based Imaginationcited by 47
2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
2022Factored Adaptation for Non-Stationary Reinforcement Learningcited by 30
2022Context is Everything: Implicit Identification for Dynamics Adaptationcited by 26
2021Block Contextual MDPs for Continual Learningcited by 25
2023State Regularized Policy Optimization on Data with Dynamics Shiftcited by 23
2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 22
2022Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imaginationcited by 21

38 more

2023GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Modelscited by 20
2023Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policiescited by 18
2022Live in the Moment: Learning Dynamics Model Adapted to Evolving Policycited by 17
2023Context Shift Reduction for Offline Meta-Reinforcement Learningcited by 17
2021Model-based Meta Reinforcement Learning using Graph Structured Surrogate Modelscited by 16
2024Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalizationcited by 16
2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglementcited by 16
2022A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learningcited by 15
2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learningcited by 13
2021Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixturecited by 12
2022Learning General World Models in a Handful of Reward-Free Deploymentscited by 12
2024Robust Fast Adaptation from Adversarially Explicit Task Distribution Generationcited by 12
2024The Evolution of Reinforcement Learning in Quantitative Finance: A Surveycited by 11
2021PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulatorscited by 10
2023Mind the Model, Not the Agent: The Primacy Bias in Model-based RLcited by 9
2024PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learningcited by 9
2024Offline Imitation Learning with Model-based Reverse Augmentationcited by 8
2022Meta-Learning Parameterized Skillscited by 7
2022Robust Imitation of a Few Demonstrations with a Backwards Modelcited by 7
2021Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environmentscited by 6
2022PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representationscited by 6
2023Online Reinforcement Learning in Non-Stationary Context-Driven Environmentscited by 6
2023Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learningcited by 6
2025Zero-Shot Reinforcement Learning Under Partial Observabilitycited by 6
2022Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Taskscited by 5
2022Phase2vec: Dynamical systems embedding with a physics-informed convolutional networkcited by 5
2023Task Aware Dreamer for Task Generalization in Reinforcement Learningcited by 5
2023Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systemscited by 5
2023AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systemscited by 5
2025Scalable In-Context Q-Learningcited by 5
2025Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalizationcited by 5
2023Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skillscited by 4
2024OMPO: A Unified Framework for RL under Policy and Dynamics Shiftscited by 4
2024QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learningcited by 4
2024ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generationscited by 4
2025Learning Policy Committees for Effective Personalization in MDPs with Diverse Taskscited by 4
2025Imagined Autocurriculacited by 4
2022Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertaintycited by 3

50 most cited of 95 All 95 (JSON)