# Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2602.02900 · HTML: https://mlsanity.com/paper/2602.02900/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Offline RL and imitation learning from data / [Diffusion and flow policies for offline RL](https://mlsanity.com/offlinerl/diffusion-and-flow-policies-for-offline-rl/)

## Builds on (most cited first, 23 of 23)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning](https://mlsanity.com/paper/2202.11566/) (2022)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [Learning Latent Space Energy-Based Prior Model](https://mlsanity.com/paper/2006.08205/) (2020)
- [VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models](https://mlsanity.com/paper/2010.00654/) (2020)
- [Offline Reinforcement Learning from Images with Latent Space Models](https://mlsanity.com/paper/2012.11547/) (2020)
- [RORL: Robust Offline Reinforcement Learning via Conservative Smoothing](https://mlsanity.com/paper/2206.02829/) (2022)
- [ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations](https://mlsanity.com/paper/2009.11193/) (2020)
- [Latent Exploration for Reinforcement Learning](https://mlsanity.com/paper/2305.20065/) (2023)
- [Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach](https://mlsanity.com/paper/2310.18677/) (2023)
- [Modeling Other Players with Bayesian Beliefs for Games with Incomplete Information](https://mlsanity.com/paper/2405.14122/) (2024)
- [Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression](https://mlsanity.com/paper/2410.19400/) (2024)

## Built on by (most cited first, 8 of 8)

- [Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics](https://mlsanity.com/paper/2602.06939/) (2026)
- [Operator-Guided Invariance Learning for Continuous Reinforcement Learning](https://mlsanity.com/paper/2605.06500/) (2026)
- [Metric-Gradient Projection for Stable Multi-Agent Policy Learning](https://mlsanity.com/paper/2605.18809/) (2026)
- [Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry](https://mlsanity.com/paper/2605.14304/) (2026)
- [Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes](https://mlsanity.com/paper/2607.27132/) (2026)
- [IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents](https://mlsanity.com/paper/2604.05157/) (2026)
- [Differentiable Policy Transport over Multi-Layer Network Feasibility Geometry](https://mlsanity.com/paper/2609.26068/) (2026)
- [Geometry-Aware Operator Families for Structured Representation Learning](https://mlsanity.com/paper/2609.33089/) (2026)

## Abstract (arXiv)

Model-based offline reinforcement learning is brittle under distribution shift: policy improvement drives rollouts into state--action regions weakly supported by the dataset, where compounding model error yields severe value overestimation. We propose Manifold-Constrained Energy-based Transition Models (MC-ETM), which train conditional energy-based transition models using a manifold projection--diffusion negative sampler. MC-ETM learns a latent manifold of next states and generates near-manifold hard negatives by perturbing latent codes and running Langevin dynamics in latent space with the learned conditional energy, sharpening the energy landscape around the dataset support and improving sensitivity to subtle out-of-distribution deviations. For policy optimization, the learned energy provides a single reliability signal: rollouts are truncated when the minimum energy over sampled next states exceeds a threshold, and Bellman backups are stabilized via pessimistic penalties based on Q-value-level dispersion across energy-guided samples. We formalize MC-ETM through a hybrid pessimistic MDP formulation and derive a conservative performance bound separating in-support evaluation error from truncation risk. Empirically, MC-ETM improves multi-step dynamics fidelity and yields higher normalized returns on standard offline control benchmarks, particularly under irregular dynamics and sparse data coverage.