Meta Reinforcement Learning
88 papers with code • 2 benchmarks • 1 datasets
Libraries
Use these libraries to find Meta Reinforcement Learning models and implementationsLatest papers
ContraBAR: Contrastive Bayes-Adaptive Deep RL
In meta reinforcement learning (meta RL), an agent seeks a Bayes-optimal policy -- the optimal policy when facing an unknown task that is sampled from some known task distribution.
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
We find a return-based uncertainty quantification for IDAQ that performs effectively.
On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks.
Procedural generation of meta-reinforcement learning tasks
The parametrization allows us to randomly generate an arbitrary number of novel simple meta-learning tasks.
Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning.
BIMRL: Brain Inspired Meta Reinforcement Learning
Inspired by recent progress in meta-RL, we introduce BIMRL, a novel multi-layer architecture along with a novel brain-inspired memory module that will help agents quickly adapt to new tasks within a few episodes.
Hypernetworks in Meta-Reinforcement Learning
In this paper, we 1) show that hypernetwork initialization is also a critical factor in meta-RL, and that naive initializations yield poor performance; 2) propose a novel hypernetwork initialization scheme that matches or exceeds the performance of a state-of-the-art approach proposed for supervised settings, as well as being simpler and more general; and 3) use this method to show that hypernetworks can improve performance in meta-RL by evaluating on multiple simulated robotics benchmarks.
Meta-Learning with Self-Improving Momentum Target
The idea of using a separately trained target model (or teacher) to improve the performance of the student model has been increasingly popular in various machine learning domains, and meta-learning is no exception; a recent discovery shows that utilizing task-wise target models can significantly boost the generalization performance.
Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
This paper addresses such a challenge by Decomposed Mutual INformation Optimization (DOMINO) for context learning, which explicitly learns a disentangled context to maximize the mutual information between the context and historical trajectories, while minimizing the state transition prediction error.
Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments
Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy.