# Upside Down Reinforcement Learning with Policy Generators

arXiv: https://arxiv.org/abs/2501.16288 · HTML: https://mlsanity.com/paper/2501.16288/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 9 of 9)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions](https://mlsanity.com/paper/1912.02875/) (2019)
- [Differentiable plasticity: training plastic neural networks with backpropagation](https://mlsanity.com/paper/1804.02464/) (2018)
- [Policy Evaluation Networks](https://mlsanity.com/paper/2002.11833/) (2020)
- [Parameter-Based Value Functions](https://mlsanity.com/paper/2006.09226/) (2020)
- [Goal-Conditioned Generators of Deep Policies](https://mlsanity.com/paper/2207.01570/) (2022)

## Built on by (most cited first, 1 of 1)

- [HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks](https://mlsanity.com/paper/2510.04898/) (2025)

## Abstract (arXiv)

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a command-conditioned generator of deep neural network policies. We accomplish this using Hypernetworks - a variant of Fast Weight Programmers, which learn to decode input commands representing a desired expected return into command-specific weight matrices. Our method, dubbed Upside Down Reinforcement Learning with Policy Generators (UDRLPG), streamlines comparable techniques by removing the need for an evaluator or critic to update the weights of the generator. To counteract the increased variance in last returns caused by not having an evaluator, we decouple the sampling probability of the buffer from the absolute number of policies in it, which, together with a simple weighting strategy, improves the empirical convergence of the algorithm. Compared with existing algorithms, UDRLPG achieves competitive performance and high returns, sometimes outperforming more complex architectures. Our experiments show that a trained generator can generalize to create policies that achieve unseen returns zero-shot. The proposed method appears to be effective in mitigating some of the challenges associated with learning highly multimodal functions. Altogether, we believe that UDRLPG represents a promising step forward in achieving greater empirical sample efficiency in RL. A full implementation of UDRLPG is publicly available at https://github.com/JacopoD/udrlpg_