# Hindsight Foresight Relabeling for Meta-Reinforcement Learning

arXiv: https://arxiv.org/abs/2109.09031 · HTML: https://mlsanity.com/paper/2109.09031/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 18 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning](https://mlsanity.com/paper/1910.08348/) (2019)
- [Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/1805.09801/) (2018)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [ProMP: Proximal Meta-Policy Search](https://mlsanity.com/paper/1810.06784/) (2018)
- [Differentiable plasticity: training plastic neural networks with backpropagation](https://mlsanity.com/paper/1804.02464/) (2018)
- [Meta-Q-Learning](https://mlsanity.com/paper/1910.00125/) (2019)
- [Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement](https://mlsanity.com/paper/2002.11089/) (2020)
- [Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices](https://mlsanity.com/paper/2008.02790/) (2020)
- [Generalized Hindsight for Reinforcement Learning](https://mlsanity.com/paper/2002.11708/) (2020)
- [Some Considerations on Learning to Explore via Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.01118/) (2018)
- [What Can Learned Intrinsic Rewards Capture?](https://mlsanity.com/paper/1912.05500/) (2019)
- [Model-based Adversarial Meta-Reinforcement Learning](https://mlsanity.com/paper/2006.08875/) (2020)
- [Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling](https://mlsanity.com/paper/2006.07178/) (2020)

## Built on by (most cited first, 4 of 4)

- [Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization](https://mlsanity.com/paper/2306.14479/) (2023)
- [Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning](https://mlsanity.com/paper/2502.03752/) (2025)
- [Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks](https://mlsanity.com/paper/2502.02834/) (2025)
- [Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review](https://mlsanity.com/paper/2505.07911/) (2025)

## Abstract (arXiv)

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at test time after experiencing only a few trajectories, the meta-training process is still sample-inefficient. Prior works have found that in the multi-task RL setting, relabeling past transitions and thus sharing experience among tasks can improve sample efficiency and asymptotic performance. We apply this idea to the meta-RL setting and devise a new relabeling method called Hindsight Foresight Relabeling (HFR). We construct a relabeling distribution using the combination of "hindsight", which is used to relabel trajectories using reward functions from the training task distribution, and "foresight", which takes the relabeled trajectories and computes the utility of each trajectory for each task. HFR is easy to implement and readily compatible with existing meta-RL algorithms. We find that HFR improves performance when compared to other relabeling methods on a variety of meta-RL tasks.