Corpus ID: 221006342

Offline Meta Reinforcement Learning

@article{Dorfman2020OfflineMR,
  title={Offline Meta Reinforcement Learning},
  author={R. Dorfman and Aviv Tamar},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.02598}
}
Consider the following problem, which we term Offline Meta Reinforcement Learning (OMRL): given the complete training histories of $N$ conventional RL agents, trained on $N$ different tasks, design a learning agent that can quickly maximize reward in a new, unseen task from the same task distribution. In particular, while each conventional RL agent explored and exploited its own different task, the OMRL agent must identify regularities in the data that lead to effective exploration/exploitation… Expand

References

SHOWING 1-10 OF 41 REFERENCES
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Meta reinforcement learning as task inference
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
Meta-Q-Learning
Meta Reinforcement Learning from observational data.
Meta-Reinforcement Learning of Structured Exploration Strategies
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
Off-Policy Deep Reinforcement Learning without Exploration
An analytic solution to discrete Bayesian reinforcement learning
...
1
2
3
4
5
...