# Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle

arXiv: https://arxiv.org/abs/2405.07473 · HTML: https://mlsanity.com/paper/2405.07473/

## Key facts

- Cited by 3 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 31 references that are in the map.
- First posted on arXiv 13 May 2024.

## 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)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Active inference on discrete state-spaces: a synthesis](https://mlsanity.com/paper/2001.07203/) (2020)
- [Reinforcement Learning through Active Inference](https://mlsanity.com/paper/2002.12636/) (2020)
- [Scaling active inference](https://mlsanity.com/paper/1911.10601/) (2019)
- [The free energy principle made simpler but not too simple](https://mlsanity.com/paper/2201.06387/) (2022)
- [Recurrent Off-policy Baselines for Memory-based Continuous Control](https://mlsanity.com/paper/2110.12628/) (2021)

## Built on by (most cited first, 3 of 3)

- [Free Energy Projective Simulation (FEPS): Active inference with interpretability](https://mlsanity.com/paper/2411.14991/) (2024)
- [Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration](https://mlsanity.com/paper/2510.05013/) (2025)
- [Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards](https://mlsanity.com/paper/2606.18963/) (2026)

## Abstract (arXiv)

In Reinforcement Learning (RL), artificial agents are trained to maximize numerical rewards by performing tasks. Exploration is essential in RL because agents must discover information before exploiting it. Two rewards encouraging efficient exploration are the entropy of action policy and curiosity for information gain. Entropy is well-established in literature, promoting randomized action selection. Curiosity is defined in a broad variety of ways in literature, promoting discovery of novel experiences. One example, prediction error curiosity, rewards agents for discovering observations they cannot accurately predict. However, such agents may be distracted by unpredictable observational noises known as curiosity traps. Based on the Free Energy Principle (FEP), this paper proposes hidden state curiosity, which rewards agents by the KL divergence between the predictive prior and posterior probabilities of latent variables. We trained six types of agents to navigate mazes: baseline agents without rewards for entropy or curiosity, and agents rewarded for entropy and/or either prediction error curiosity or hidden state curiosity. We find entropy and curiosity result in efficient exploration, especially both employed together. Notably, agents with hidden state curiosity demonstrate resilience against curiosity traps, which hinder agents with prediction error curiosity. This suggests implementing the FEP may enhance the robustness and generalization of RL models, potentially aligning the learning processes of artificial and biological agents.