Policy Optimization (PO) algorithms have been proven particularly suited to handle the high-dimensionality of real-world continuous control tasks. In this context, Trust Region Policy Optimization methods represent a popular approach to stabilize the policy updates. These usually rely on the Kullback-Leibler (KL) divergence to limit the change in the policy. The Wasserstein distance represents a natural alternative, in place of the KL divergence, to define trust regions or to regularize the objective function. However, state-of-the-art works either resort to its approximations or do not provide an algorithm for continuous state-action spaces, reducing the applicability of the method.In this paper, we explore optimal transport discrepancies (which include the Wasserstein distance) to define trust regions, and we propose a novel algorithm - Optimal Transport Trust Region Policy Optimization (OT-TRPO) - for continuous state-action spaces. We circumvent the infinite-dimensional optimization problem for PO by providing a one-dimensional dual reformulation for which strong duality holds.We then analytically derive the optimal policy update given the solution of the dual problem. This way, we bypass the computation of optimal transport costs and of optimal transport maps, which we implicitly characterize by solving the dual formulation.Finally, we provide an experimental evaluation of our approach across various control tasks. Our results show that optimal transport discrepancies can offer an advantage over state-of-the-art approaches.

Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization (TRPO) on the MetaWorld ML10 benchmark, a challenging suite of ten diverse robotic manipulation tasks. We implement and analyze MAML-TRPO's ability to learn a universal initialization that facilitates few-shot adaptation across semantically different manipulation behaviors including pushing, picking, and drawer manipulation. Our experiments demonstrate that MAML achieves effective one-shot adaptation with clear performance improvements after a single gradient update, reaching final success rates of 21.0% on training tasks and 13.2% on held-out test tasks. However, we observe a generalization gap that emerges during meta-training, where performance on test tasks plateaus while training task performance continues to improve. Task-level analysis reveals high variance in adaptation effectiveness, with success rates ranging from 0% to 80% across different manipulation skills. These findings highlight both the promise and current limitations of gradient-based meta-learning for diverse robotic manipulation, and suggest directions for future work in task-aware adaptation and structured policy architectures.

Policy Optimization (PO) algorithms have been proven particularly suited to handle the high-dimensionality of real-world continuous control tasks. In this context, Trust Region Policy Optimization methods represent a popular approach to stabilize the policy updates. These usually rely on the Kullback-Leibler (KL) divergence to limit the change in the policy. The Wasserstein distance represents a natural alternative, in place of the KL divergence, to define trust regions or to regularize the objective function. However, state-of-the-art works either resort to its approximations or do not provide an algorithm for continuous state-action spaces, reducing the applicability of the method.In this paper, we explore optimal transport discrepancies (which include the Wasserstein distance) to define trust regions, and we propose a novel algorithm - Optimal Transport Trust Region Policy Optimization (OT-TRPO) - for continuous state-action spaces.

Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implement such a mapping via a neural network (NN) whose parameters are optimized using stochastic gradient descent. However, PG methods are prone to large policy updates that can render learning inefficient. Trust region algorithms, like Trust Region Policy Optimization (TRPO), constrain the policy update step, ensuring monotonic improvements. This paper introduces low-rank matrix-based models as an efficient alternative for estimating the parameters of TRPO algorithms. By gathering the stochastic policy's parameters into a matrix and applying matrix-completion techniques, we promote and enforce low rank. Our numerical studies demonstrate that low-rank matrix-based policy models effectively reduce both computational and sample complexities compared to NN models, while maintaining comparable aggregated rewards.

The human brain is wired to be able to learn new things--and in all kinds of different ways, from imitating others to watching online explainer videos. What if robots could do the same thing? It is a question that ACM Prize recipient Pieter Abbeel, professor at the University of California, Berkeley and director of the Berkeley Robot Learning Lab, has spent his career researching. Here, we speak with Abbeel about his work and about the techniques he has developed to make it easier to teach robots. Let's start with deep reinforcement learning and the method you developed called Trust Region Policy Optimization.

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on complex tasks, but their real-world adoption remains limited because they often require significant amounts of data to succeed. When combined with small sample sizes, these methods can result in unstable learning due to their reliance on high-dimensional sample-based estimates. In this work, we develop techniques to control the uncertainty introduced by these estimates. We leverage these techniques to propose a deep policy optimization approach designed to produce stable performance even when data is scarce. The resulting algorithm, Uncertainty-Aware Trust Region Policy Optimization, generates robust policy updates that adapt to the level of uncertainty present throughout the learning process.

Although duality is used extensively in certain fields, such as supervised learning in machine learning, it has been much less explored in others, such as reinforcement learning (RL). In this paper, we show how duality is involved in a variety of RL work, from that which spearheaded the field, such as Richard Bellman's value iteration, to that which was done within just the past few years yet has already had significant impact, such as TRPO, A3C, and GAIL. We show that duality is not uncommon in reinforcement learning, especially when value iteration, or dynamic programming, is used or when first or second order approximations are made to transform initially intractable problems into tractable convex programs.

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art performance when used in reinforcement learning across a wide range of tasks. However, the algorithm suffers from a number of drawbacks including: lack of stepsize selection criterion, and slow convergence. We investigate the use of a trust region method using dogleg step and a Quasi-Newton approximation for the Hessian for policy optimization. We demonstrate through numerical experiments over a wide range of challenging continuous control tasks that our particular choice is efficient in terms of number of samples and improves performance

As reinforcement learning continues to drive machine intelligence beyond its conventional boundary, unsubstantial practices in sparse reward environment severely limit further applications in a broader range of advanced fields. Motivated by the demand for an effective deep reinforcement learning algorithm that accommodates sparse reward environment, this paper presents Hindsight Trust Region Policy Optimization (Hindsight TRPO), a method that efficiently utilizes interactions in sparse reward conditions and maintains learning stability by restricting variance during the policy update process. Firstly, the hindsight methodology is expanded to TRPO, an advanced and efficient on-policy policy gradient method. Then, under the condition that the distributions are close, the KL-divergence is appropriately approximated by another $f$-divergence. Such approximation results in the decrease of variance during KL-divergence estimation and alleviates the instability during policy update. Experimental results on both discrete and continuous benchmark tasks demonstrate that Hindsight TRPO converges steadily and significantly faster than previous policy gradient methods. It achieves effective performances and high data-efficiency for training policies in sparse reward environments.

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraint, normalizing flows policy can generate samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps avoid bad local optima. We show that normalizing flows policy significantly improves upon factorized Gaussian policy baseline, with both TRPO and ACKTR, especially on tasks with complex dynamics such as Humanoid.