Being able to discover diverse useful skills without external reward functions is beneficial in reinforcement learning research. Previous unsupervised skill discovery approaches mainly train different skills in parallel. Although impressive results have been provided, we found that parallel training procedure can sometimes block exploration when the state visited by different skills overlap, which leads to poor state coverage and restricts the diversity of learned skills. In this paper, we take a deeper look into this phenomenon and propose a novel framework to address this issue, which we call Recurrent Skill Training (ReST). Instead of training all the skills in parallel, ReST trains different skills one after another recurrently, along with a state coverage based intrinsic reward. We conduct experiments on a number of challenging 2D navigation environments and robotic locomotion environments. Evaluation results show that our proposed approach outperforms previous parallel training approaches in terms of state coverage and skill diversity. Videos of the discovered skills are available at https://sites.google.com/view/neurips22-rest.

Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity. However, existing methods often face challenges in simultaneously optimizing for these two conflicting objectives. In this work, we propose a new method, Adaptive Multi-objective Projection for balancing Exploration and skill Diversification (AMPED), which explicitly addresses both: during pre-training, a gradient-surgery projection balances the exploration and diversity gradients, and during fine-tuning, a skill selector exploits the learned diversity by choosing skills suited to downstream tasks. Our approach achieves performance that surpasses SBRL baselines across various benchmarks. Through an extensive ablation study, we identify the role of each component and demonstrate that each element in AMPED is contributing to performance. We further provide theoretical and empirical evidence that, with a greedy skill selector, greater skill diversity reduces fine-tuning sample complexity. These results highlight the importance of explicitly harmonizing exploration and diversity and demonstrate the effectiveness of AMPED in enabling robust and generalizable skill learning. Project Page: https://geonwoo.me/amped/

Scaling unsupervised skill discovery algorithms to high-DoF agents remains challenging. As dimensionality increases, the exploration space grows exponentially, while the manifold of meaningful skills remains limited. Therefore, semantic meaningfulness becomes essential to effectively guide exploration in high-dimensional spaces. In this work, we present **Reference-Grounded Skill Discovery (RGSD)**, a novel algorithm that grounds skill discovery in a semantically meaningful latent space using reference data. RGSD first performs contrastive pretraining to embed motions on a unit hypersphere, clustering each reference trajectory into a distinct direction. This grounding enables skill discovery to simultaneously involve both imitation of reference behaviors and the discovery of semantically related diverse behaviors. On a simulated SMPL humanoid with $359$-D observations and $69$-D actions, RGSD successfully imitates skills such as walking, running, punching, and sidestepping, while also discover variations of these behaviors. In downstream locomotion tasks, RGSD leverages the discovered skills to faithfully satisfy user-specified style commands and outperforms imitation-learning baselines, which often fail to maintain the commanded style. Overall, our results suggest that lightweight reference-grounding offers a practical path to discovering semantically rich and structured skills in high-DoF systems.

Exploration is crucial for enabling legged robots to learn agile locomotion behaviors that can overcome diverse obstacles. However, such exploration is inherently challenging, and we often rely on extensive reward engineering, expert demonstrations, or curriculum learning - all of which limit generalizability. In this work, we propose Skill Discovery as Exploration (SDAX), a novel learning framework that significantly reduces human engineering effort. SDAX leverages unsupervised skill discovery to autonomously acquire a diverse repertoire of skills for overcoming obstacles. To dynamically regulate the level of exploration during training, SDAX employs a bi-level optimization process that autonomously adjusts the degree of exploration. We demonstrate that SDAX enables quadrupedal robots to acquire highly agile behaviors including crawling, climbing, leaping, and executing complex maneuvers such as jumping off vertical walls. Finally, we deploy the learned policy on real hardware, validating its successful transfer to the real world.

Being able to discover diverse useful skills without external reward functions is beneficial in reinforcement learning research. Previous unsupervised skill discovery approaches mainly train different skills in parallel. Although impressive results have been provided, we found that parallel training procedure can sometimes block exploration when the state visited by different skills overlap, which leads to poor state coverage and restricts the diversity of learned skills. In this paper, we take a deeper look into this phenomenon and propose a novel framework to address this issue, which we call Recurrent Skill Training (ReST). Instead of training all the skills in parallel, ReST trains different skills one after another recurrently, along with a state coverage based intrinsic reward.

There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these advances, challenges remain: current methods require significant online interaction, fail to leverage vast amounts of available task-agnostic data and typically lack a quantitative measure of skill utility. We address these challenges by proposing a principled offline algorithm for unsupervised skill discovery that, in addition to maximizing diversity, ensures that each learned skill imitates state-only expert demonstrations to a certain degree. Our main analytical contribution is to connect Fenchel duality, reinforcement learning, and unsupervised skill discovery to maximize a mutual information objective subject to KL-divergence state occupancy constraints. Furthermore, we demonstrate the effectiveness of our method on the standard offline benchmark D4RL and on a custom offline dataset collected from a 12-DoF quadruped robot for which the policies trained in simulation transfer well to the real robotic system.

Learning diverse and qualified behaviors for utilization and adaptation without supervision is a key ability of intelligent creatures. Ideal unsupervised skill discovery methods are able to produce diverse and qualified skills in the absence of extrinsic reward, while the discovered skill set can efficiently adapt to downstream tasks in various ways. Maximizing the Mutual Information (MI) between skills and visited states can achieve ideal skill-conditioned behavior distillation in theory. However, it's difficult for recent advanced methods to well balance behavioral quality (exploration) and diversity (exploitation) in practice, which may be attributed to the unreasonable MI estimation by their rigid intrinsic reward design. In this paper, we propose Contrastive multi-objectives Skill Discovery (ComSD) which tries to mitigate the quality-versus-diversity conflict of discovered behaviors through a more reasonable MI estimation and a dynamically weighted intrinsic reward. ComSD proposes to employ contrastive learning for a more reasonable estimation of skill-conditioned entropy in MI decomposition. In addition, a novel weighting mechanism is proposed to dynamically balance different entropy (in MI decomposition) estimations into a novel multi-objective intrinsic reward, to improve both skill diversity and quality. For challenging robot behavior discovery, ComSD can produce a qualified skill set consisting of diverse behaviors at different activity levels, which recent advanced methods cannot. On numerical evaluations, ComSD exhibits state-of-the-art adaptation performance, significantly outperforming recent advanced skill discovery methods across all skill combination tasks and most skill finetuning tasks. Codes will be released at https://github.com/liuxin0824/ComSD.

In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI objective tends to learn simple and static skills and may hinder exploration. In this paper, we propose a novel unsupervised skill discovery method through contrastive learning among behaviors, which makes the agent produce similar behaviors for the same skill and diverse behaviors for different skills. Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective. Meanwhile, our method implicitly increases the state entropy to obtain better state coverage. We evaluate our method on challenging mazes and continuous control tasks. The results show that our method generates diverse and far-reaching skills, and also obtains competitive performance in downstream tasks compared to the state-of-the-art methods.

Unsupervised Reinforcement Learning (RL), where RL agents pre-train with self-supervised rewards, is an emerging paradigm for developing RL agents that are capable of generalization. Recently, we released the Unsupervised RL Benchmark (URLB) which we covered in a previous post. A surprising finding was that competence-based algorithms significantly underperformed other categories. In this post we will demystify what has been holding back competence-based methods and introduce Contrastive Intrinsic Control (CIC), a new competence-based algorithm that is the first to achieve leading results on URLB. To recap, competence-based methods (which we will cover in detail) maximize the mutual information between states and skills (e.g.