paper-with-me

Papers

Domain Randomization via Entropy Maximization

2023-11-03 · Gabriele Tiboni, Pascal Klink, Jan Peters, Tatiana Tommasi, Carlo D'Eramo, Georgia Chalvatzaki

Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hinges on the choice of the sampling distribution of the dynamics parameters, since high variability is crucial to regularize the agent's behavior but notoriously leads to overly conservative policies when randomizing excessively. In this paper, we propose a novel approach to address sim-to-real transfer, which automatically shapes dynamics distributions during training in simulation without requiring real-world data. We introduce DOmain RAndomization via Entropy MaximizatiON (DORAEMON), a constrained optimization problem that directly maximizes the entropy of the training distribution while retaining generalization capabilities. In achieving this, DORAEMON gradually increases the diversity of sampled dynamics parameters as long as the probability of success of the current policy is sufficiently high. We empirically validate the consistent benefits of DORAEMON in obtaining highly adaptive and generalizable policies, i.e. solving the task at hand across the widest range of dynamics parameters, as opposed to representative baselines from the DR literature. Notably, we also demonstrate the Sim2Real applicability of DORAEMON through its successful zero-shot transfer in a robotic manipulation setup under unknown real-world parameters.

📄 PDF Abstract BibTeX arXiv:2311.01885

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

2025-02-03 · Aidan Curtis, Eric Li, Michael Noseworthy, Nishad Gothoskar 외

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned polic…

Out-of-Distribution Detection

Entropy Minimization vs. Diversity Maximization for Domain Adaptation

2020-02-05 · Xiaofu Wu, Suofei hang, Quan Zhou, Zhen Yang 외

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to a…

DiversityDomain AdaptationUnsupervised Domain Adaptation

How to Explore with Belief: State Entropy Maximization in POMDPs

2024-06-04 · Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti

Recent works have studied *state entropy maximization* in reinforcement learning, in which the agent's objective is to learn a policy inducing high entropy over states visitation (Hazan et al., 2019). They typically assu…

Hallucination

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough

2024-06-18 · Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti

The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied. However, lit…

Provable Sim-to-Real Transfer via Offline Domain Randomization

2025-06-11 · Arnaud Fickinger, Abderrahim Bendahi, Stuart Russell

Reinforcement-learning agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulato…