Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. However, empowerment often leads to static skills, and pure exploration only maximizes the state coverage rather than learning useful behaviors. In this paper, we propose a novel unsupervised RL framework via an ensemble of skills, where each skill performs partition exploration based on the state prototypes. Thus, each skill can explore the clustered area locally, and the ensemble skills maximize the overall state coverage. We adopt state-distribution constraints for the skill occupancy and the desired cluster for learning distinguishable skills. Theoretical analysis is provided for the state entropy and the resulting skill distributions. Based on extensive experiments on several challenging tasks, we find our method learns well-explored ensemble skills and achieves superior performance in various downstream tasks compared to previous methods.
Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However, entropy-based exploration struggles in large-scale state spaces (e.g., images), and empowerment-based methods with Mutual Information (MI) estimations have limitations in state exploration. To address these challenges, we propose a novel skill discovery objective that maximizes the deviation of the state density of one skill from the explored regions of other skills, encouraging inter-skill state diversity similar to the initial MI objective. For state-density estimation, we construct a novel conditional autoencoder with soft modularization for different skill policies in high-dimensional space. Meanwhile, to incentivize intra-skill exploration, we formulate an intrinsic reward based on the learned autoencoder that resembles count-based exploration in a compact latent space. Through extensive experiments in challenging state and image-based tasks, we find our method learns meaningful skills and achieves superior performance in various downstream tasks.
Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual information between states and skills but lacks sufficient theoretical analysis, e.g., how well its learned skills can initialize a downstream task's policy. Our new theoretical analysis in this paper shows that the diversity and separability of learned skills are fundamentally critical to downstream task adaptation but MISL does not necessarily guarantee these properties. To complement MISL, we propose a novel disentanglement metric LSEPIN. Moreover, we build an information-geometric connection between LSEPIN and downstream task adaptation cost. For better geometric properties, we investigate a new strategy that replaces the KL divergence in information geometry with Wasserstein distance. We extend the geometric analysis to it, which leads to a novel skill-learning objective WSEP. It is theoretically justified to be helpful to downstream task adaptation and it is capable of discovering more initial policies for downstream tasks than MISL. We finally propose another Wasserstein distance-based algorithm PWSEP that can theoretically discover all optimal initial policies.
Quality-Diversity (QD) algorithms have shown remarkable success in discovering diverse, high-performing solutions, but rely heavily on hand-crafted behavioral descriptors that constrain exploration to predefined notions of diversity. Leveraging the equivalence between policies and occupancy measures, we present a theoretically grounded approach to automatically generate behavioral descriptors by embedding the occupancy measures of policies in Markov Decision Processes. Our method, AutoQD, leverages random Fourier features to approximate the Maximum Mean Discrepancy (MMD) between policy occupancy measures, creating embeddings whose distances reflect meaningful behavioral differences. A low-dimensional projection of these embeddings that captures the most behaviorally significant dimensions is then used as behavioral descriptors for off-the-shelf QD methods. We prove that our embeddings converge to true MMD distances between occupancy measures as the number of sampled trajectories and embedding dimensions increase. Through experiments in multiple continuous control tasks we demonstrate AutoQD's ability in discovering diverse policies without predefined behavioral descriptors, presenting a well-motivated alternative to prior methods in unsupervised Reinforcement Learning and QD optimization. Our approach opens new possibilities for open-ended learning and automated behavior discovery in sequential decision making settings without requiring domain-specific knowledge.
We present an interpretability framework for unsupervised reinforcement learning (URL) agents, aimed at understanding how intrinsic motivation shapes attention, behavior, and representation learning. We analyze five agents DQN, RND, ICM, PPO, and a Transformer-RND variant trained on procedurally generated environments, using Grad-CAM, Layer-wise Relevance Propagation (LRP), exploration metrics, and latent space clustering. To capture how agents perceive and adapt over time, we introduce two metrics: attention diversity, which measures the spatial breadth of focus, and attention change rate, which quantifies temporal shifts in attention. Our findings show that curiosity-driven agents display broader, more dynamic attention and exploratory behavior than their extrinsically motivated counterparts. Among them, TransformerRND combines wide attention, high exploration coverage, and compact, structured latent representations. Our results highlight the influence of architectural inductive biases and training signals on internal agent dynamics. Beyond reward-centric evaluation, the proposed framework offers diagnostic tools to probe perception and abstraction in RL agents, enabling more interpretable and generalizable behavior.
Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing approaches suffer from several limitations: they may require running an RL process on each downstream task to achieve a satisfactory performance, they may need access to datasets with good coverage or well-curated task-specific samples, or they may pre-train policies with unsupervised losses that are poorly correlated with the downstream tasks of interest. In this paper, we introduce a novel algorithm regularizing unsupervised RL towards imitating trajectories from unlabeled behavior datasets. The key technical novelty of our method, called Forward-Backward Representations with Conditional-Policy Regularization, is to train forward-backward representations to embed the unlabeled trajectories to the same latent space used to represent states, rewards, and policies, and use a latent-conditional discriminator to encourage policies to ``cover'' the states in the unlabeled behavior dataset. As a result, we can learn policies that are well aligned with the behaviors in the dataset, while retaining zero-shot generalization capabilities for reward-based and imitation tasks. We demonstrate the effectiveness of this new approach in a challenging humanoid control problem: leveraging observation-only motion capture datasets, we train Meta Motivo, the first humanoid behavioral foundation model that can be prompted to solve a variety of whole-body tasks, including motion tracking, goal reaching, and reward optimization. The resulting model is capable of expressing human-like behaviors and it achieves competitive performance with task-specific methods while outperforming state-of-the-art unsupervised RL and model-based baselines.
Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstream tasks. As the agent cannot access extrinsic rewards during unsupervised exploration, existing methods design intrinsic rewards to model the explored data and encourage further exploration. However, the explored data are always heterogeneous, posing the requirements of powerful representation abilities for both intrinsic reward models and pre-trained policies. In this work, we propose the Exploratory Diffusion Model (ExDM), which leverages the strong expressive ability of diffusion models to fit the explored data, simultaneously boosting exploration and providing an efficient initialization for downstream tasks. Specifically, ExDM can accurately estimate the distribution of collected data in the replay buffer with the diffusion model and introduces the score-based intrinsic reward, encouraging the agent to explore less-visited states. After obtaining the pre-trained policies, ExDM enables rapid adaptation to downstream tasks. In detail, we provide theoretical analyses and practical algorithms for fine-tuning diffusion policies, addressing key challenges such as training instability and computational complexity caused by multi-step sampling. Extensive experiments demonstrate that ExDM outperforms existing SOTA baselines in efficient unsupervised exploration and fast fine-tuning downstream tasks, especially in structurally complicated environments.
Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (Skild), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding Skild is that skills that induce <b>diverse interactions</b> between state factors are often more valuable for solving downstream tasks. To this end, Skild develops a novel skill learning objective that explicitly encourages the mastering of skills that effectively induce different interactions within an environment. We evaluate Skild in several domains with challenging, long-horizon sparse reward tasks including a realistic simulated household robot domain, where Skild successfully learns skills with clear semantic meaning and shows superior performance compared to existing unsupervised reinforcement learning methods that only maximize state coverage.
Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However, neither method alone results in an agent that will consistently learn intelligent behavior across environments. In an effort to find a single entropy-based method that will encourage emergent behaviors in any environment, we propose an agent that can adapt its objective online, depending on the entropy conditions by framing the choice as a multi-armed bandit problem. We devise a novel intrinsic feedback signal for the bandit, which captures the agent's ability to control the entropy in its environment. We demonstrate that such agents can learn to control entropy and exhibit emergent behaviors in both high- and low-entropy regimes and can learn skillful behaviors in benchmark tasks. Videos of the trained agents and summarized findings can be found on our project page https://sites.google.com/view/surprise-adaptive-agents
One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key to enhancing the robustness and sample efficiency of RL algorithms. However, learning representations in RL settings for visuotactile data poses significant challenges, particularly due to the high dimensionality of the data and the complexity involved in correlating visual and tactile inputs with the dynamic environment and task objectives. To address these challenges, we propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL). Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. Our method is agnostic to the RL algorithm, thus enabling its integration with any available RL algorithm. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks. This is evidenced by faster convergence rates and higher cumulative rewards per episode, compared to standard RL algorithms without our representation learning approach.
The authors of 'Unsupervised Reinforcement Learning in Multiple environments' propose a method, alpha-MEPOL, to tackle unsupervised RL across multiple environments. They pre-train a task-agnostic exploration policy using interactions from an entire environment class and then fine-tune this policy for various tasks using supervision. We expanded upon this work, with the goal of improving performance. We primarily propose and experiment with five new modifications to the original work: sampling trajectories using an entropy-based probability distribution, dynamic alpha, higher KL Divergence threshold, curiosity-driven exploration, and alpha-percentile sampling on curiosity. Dynamic alpha and higher KL-Divergence threshold both provided a significant improvement over the baseline from the earlier work. PDF-sampling failed to provide any improvement due to it being approximately equivalent to the baseline method when the sample space is small. In high-dimensional environments, the addition of curiosity-driven exploration enhances learning by encouraging the agent to seek diverse experiences and explore the unknown more. However, its benefits are limited in low-dimensional and simpler environments where exploration possibilities are constrained and there is little that is truly unknown to the agent. Overall, some of our experiments did boost performance over the baseline and there are a few directions that seem promising for further research.
We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. In our framework, the agent receives task instructions grounded in a training environment from large language models. Then, a vision-language model guides the agent in learning the multi-task language-conditioned policy by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment while prior unsupervised skill discovery methods struggle. Additionally, we discuss observed challenges of using off-the-shelf foundation models as teachers and our efforts to address them.
Humans possess the ability to draw on past experiences explicitly when learning new tasks and applying them accordingly. We believe this capacity for self-referencing is especially advantageous for reinforcement learning agents in the unsupervised pretrain-then-finetune setting. During pretraining, an agent's past experiences can be explicitly utilized to mitigate the nonstationarity of intrinsic rewards. In the finetuning phase, referencing historical trajectories prevents the unlearning of valuable exploratory behaviors. Motivated by these benefits, we propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information and enhance agent performance within the pretrain-finetune paradigm. Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark for model-free methods, recording an 86% IQM and a 16% Optimality Gap. Additionally, it improves current algorithms by up to 17% IQM and reduces the Optimality Gap by 31%. Beyond performance enhancement, the Self-Reference add-on also increases sample efficiency, a crucial attribute for real-world applications.
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI models like ChatGPT depend on fine-tuning through human demonstrations, demanding extensive human input and domain expertise. This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation. To address this limitation, we propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data. Drawing inspiration from unsupervised reinforcement learning (RL) pretraining, EAI achieves exploration within the natural language space. We accomplish this by harnessing large language models to assess the novelty of generated content. Our approach employs two key components: an actor that generates novel content following exploration principles and a critic that evaluates the generated content, offering critiques to guide the actor. Empirical evaluations demonstrate that EAI significantly boosts model performance on complex reasoning tasks, addressing the limitations of human-intensive supervision.
Unsupervised pre-training strategies have proven to be highly effective in natural language processing and computer vision. Likewise, unsupervised reinforcement learning (RL) holds the promise of discovering a variety of potentially useful behaviors that can accelerate the learning of a wide array of downstream tasks. Previous unsupervised RL approaches have mainly focused on pure exploration and mutual information skill learning. However, despite the previous attempts, making unsupervised RL truly scalable still remains a major open challenge: pure exploration approaches might struggle in complex environments with large state spaces, where covering every possible transition is infeasible, and mutual information skill learning approaches might completely fail to explore the environment due to the lack of incentives. To make unsupervised RL scalable to complex, high-dimensional environments, we propose a novel unsupervised RL objective, which we call Metric-Aware Abstraction (METRA). Our main idea is, instead of directly covering the entire state space, to only cover a compact latent space $Z$ that is metrically connected to the state space $S$ by temporal distances. By learning to move in every direction in the latent space, METRA obtains a tractable set of diverse behaviors that approximately cover the state space, being scalable to high-dimensional environments. Through our experiments in five locomotion and manipulation environments, we demonstrate that METRA can discover a variety of useful behaviors even in complex, pixel-based environments, being the first unsupervised RL method that discovers diverse locomotion behaviors in pixel-based Quadruped and Humanoid. Our code and videos are available at https://seohong.me/projects/metra/
This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Unsupervised skill discovery seeks to acquire different useful skills without extrinsic reward via unsupervised Reinforcement Learning (RL), with the discovered skills efficiently adapting to multiple downstream tasks in various ways. However, recent advanced skill discovery methods struggle to well balance state exploration and skill diversity, particularly when the potential skills are rich and hard to discern. In this paper, we propose \textbf{Co}ntrastive dyna\textbf{m}ic \textbf{S}kill \textbf{D}iscovery \textbf{(ComSD)}\footnote{Code and videos: https://github.com/liuxin0824/ComSD} which generates diverse and exploratory unsupervised skills through a novel intrinsic incentive, named contrastive dynamic reward. It contains a particle-based exploration reward to make agents access far-reaching states for exploratory skill acquisition, and a novel contrastive diversity reward to promote the discriminability between different skills. Moreover, a novel dynamic weighting mechanism between the above two rewards is proposed to balance state exploration and skill diversity, which further enhances the quality of the discovered skills. Extensive experiments and analysis demonstrate that ComSD can generate diverse behaviors at different exploratory levels for multi-joint robots, enabling state-of-the-art adaptation performance on challenging downstream tasks. It can also discover distinguishable and far-reaching exploration skills in the challenging tree-like 2D maze.
Recently, methods for learning diverse skills to generate various behaviors without external rewards have been actively studied as a form of unsupervised reinforcement learning. However, most of the existing methods learn a finite number of discrete skills, and thus the variety of behaviors that can be exhibited with the learned skills is limited. In this paper, we propose a novel method for learning potentially an infinite number of different skills, which is named discovery of continuous skills on a sphere (DISCS). In DISCS, skills are learned by maximizing mutual information between skills and states, and each skill corresponds to a continuous value on a sphere. Because the representations of skills in DISCS are continuous, infinitely diverse skills could be learned. We examine existing methods and DISCS in the MuJoCo Ant robot control environments and show that DISCS can learn much more diverse skills than the other methods.
We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard stochastic gradient descent and the gradient clipping method. The output layer is updated using clipped gradients, the rest of the neural network is updated using standard gradients. Updating the output layer using clipped gradient stabilizes it. We show that the remaining layers are automatically stabilized provided the neural network is only composed of squashing (compact range) activations. We also present a novel squashing activation function - it is obtained by modifying a Gaussian Error Linear Unit (GELU) to have compact range - we call it Truncated GELU (tGELU). Unlike other squashing activations, such as sigmoid, the range of tGELU can be explicitly specified. As a consequence, the problem of vanishing gradients that arise due to a small range, e.g., in the case of a sigmoid activation, is eliminated. We prove that a NN composed of squashing activations (tGELU, sigmoid, etc.), when updated using the algorithm presented herein, is numerically stable and has consistent performance (low variance). The theory is supported by extensive experiments. Within reinforcement learning, as a consequence of our study, we show that target networks in Deep Q-Learning can be omitted, greatly speeding up learning and alleviating memory requirements. Cross-entropy based classification algorithms that suffer from high variance issues are more consistent when trained using our framework. One symptom of numerical instability in training is the high variance of the neural network update values. We show, in theory and through experiments, that our algorithm updates have low variance, and the training loss reduces in a smooth manner.
This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models. Specifically, a novel architecture is proposed that uses a heterogeneous loss function, called CRC loss, to learn improved visual features which can then be used for policy learning in RL. The CRC-loss function is a combination of three individual loss functions, namely, contrastive, reconstruction and consistency loss. The feature representation is learned in parallel to the policy learning while sharing the weight updates through a Siamese Twin encoder model. This encoder model is augmented with a decoder network and a feature projection network to facilitate computation of the above loss components. Through empirical analysis involving latent feature visualization, an attempt is made to provide an insight into the role played by this loss function in learning new action-dependent features and how they are linked to the complexity of the problems being solved. The proposed architecture, called CRC-RL, is shown to outperform the existing state-of-the-art methods on the challenging Deep mind control suite environments by a significant margin thereby creating a new benchmark in this field.
Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate knowledge and exploration, skills may provide control only over a restricted area of the environment, limiting their applicability. Furthermore, it is unclear how to leverage the learned skill behaviors for adapting to downstream tasks in a data-efficient manner. We present Choreographer, a model-based agent that exploits its world model to learn and adapt skills in imagination. Our method decouples the exploration and skill learning processes, being able to discover skills in the latent state space of the model. During adaptation, the agent uses a meta-controller to evaluate and adapt the learned skills efficiently by deploying them in parallel in imagination. Choreographer is able to learn skills both from offline data, and by collecting data simultaneously with an exploration policy. The skills can be used to effectively adapt to downstream tasks, as we show in the URL benchmark, where we outperform previous approaches from both pixels and states inputs. The learned skills also explore the environment thoroughly, finding sparse rewards more frequently, as shown in goal-reaching tasks from the DMC Suite and Meta-World. Website and code: https://skillchoreographer.github.io/