DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episode sessions - parts of the episode where the latent state is fixed - and propose three key modifications to existing meta-RL methods: consistency of latent information within sessions, session masking, and prior latent conditioning. We demonstrate the importance of these modifications in various domains, ranging from discrete Gridworld environments to continuous-control and simulated robot assistive tasks, demonstrating that DynaMITE-RL significantly outperforms state-of-the-art baselines in sample efficiency and inference returns.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 25 Feb 2024.
Builds on
33 of 50 references.
References · 33
- 2017Attention Is All You Needcited by 59,932
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2016OpenAI Gymcited by 1,684
- 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
- 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 750
- 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
- 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
- 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
- 2016Learning to reinforcement learncited by 369
21 more
- 2019Reinforcement Learning in Healthcare: A Surveycited by 308
- 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
- 2020A Survey on Conversational Recommender Systemscited by 142
- 2023A Tutorial on Meta-Reinforcement Learningcited by 102
- 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 99
- 2018ProMP: Proximal Meta-Policy Searchcited by 91
- 2019RecSim: A Configurable Simulation Platform for Recommender Systemscited by 91
- 2023Preference Transformer: Modeling Human Preferences using Transformers for RLcited by 77
- 2019Meta reinforcement learning as task inferencecited by 75
- 2021RL for Latent MDPs: Regret Guarantees and a Lower Boundcited by 69
- 2019Assistive Gym: A Physics Simulation Framework for Assistive Roboticscited by 44
- 2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
- 2017Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processescited by 28
- 2020Reinforcement Learning based Control of Imitative Policies for Near-Accident Drivingcited by 23
- 2022An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Contextcited by 15
- 2023Recurrent Hypernetworks are Surprisingly Strong in Meta-RLcited by 15
- 2021On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learningcited by 14
- 2018Bayesian Policy Optimization for Model Uncertaintycited by 12
- 2023Reinforcement Learning with History-Dependent Dynamic Contextscited by 11
- 2023ContraBAR: Contrastive Bayes-Adaptive Deep RLcited by 9
- 2019Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Modelscited by 7
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.