Meta Reinforcement Learning
88 papers with code • 2 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Meta Reinforcement Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Meta Reinforcement Learning models and implementations
Meta-World Benchmark
Most implemented papers
Meta Reinforcement Learning with Task Embedding and Shared Policy
llan-ml/tesp
•
•
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization.
Meta-Q-Learning
amazon-research/meta-q-learning
•
•
ICLR 2020
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL).
Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads
suneelbelkhale/model-based-meta-rl-for-flight
•
•
Our experiments demonstrate that our online adaptation approach outperforms non-adaptive methods on a series of challenging suspended payload transportation tasks.
Learning Robust State Abstractions for Hidden-Parameter Block MDPs
facebookresearch/mtrl
•
•
ICLR 2021
Further, we provide transfer and generalization bounds based on task and state similarity, along with sample complexity bounds that depend on the aggregate number of samples across tasks, rather than the number of tasks, a significant improvement over prior work that use the same environment assumptions.
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
Learning a new task often requires both exploring to gather task-relevant information and exploiting this information to solve the task.
Offline Meta-Reinforcement Learning with Advantage Weighting
That is, in offline meta-RL, we meta-train on fixed, pre-collected data from several tasks in order to adapt to a new task with a very small amount (less than 5 trajectories) of data from the new task.
learn2learn: A Library for Meta-Learning Research
Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility.
Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviours
nvecoven/nmd_net
•
•
Animals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack.
Causal Reasoning from Meta-reinforcement Learning
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents.
Concurrent Meta Reinforcement Learning
In this multi-agent setting, a set of parallel agents are executed in the same environment and each of these "rollout" agents are given the means to communicate with each other.
