English
Related papers

Related papers: Muesli: Combining Improvements in Policy Optimizat…

200 papers

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts.…

Machine Learning · Computer Science 2021-10-27 Valentin Charvet , Bjørn Sand Jensen , Roderick Murray-Smith

Policies developed through Reinforcement Learning (RL) and Imitation Learning (IL) have shown great potential in continuous control tasks, but real-world applications often require adapting trained policies to unforeseen requirements. While…

Robotics · Computer Science 2025-03-17 Pengcheng Wang , Chenran Li , Catherine Weaver , Kenta Kawamoto , Masayoshi Tomizuka , Chen Tang , Wei Zhan

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Model-based policy optimization often struggles with inaccurate system dynamics models, leading to suboptimal closed-loop performance. This challenge is especially evident in Model Predictive Control (MPC) policies, which rely on the model…

Systems and Control · Electrical Eng. & Systems 2026-04-21 Riccardo Zuliani , Efe C. Balta , John Lygeros

AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey…

Machine Learning · Computer Science 2019-06-03 Isaac Lage , Daphna Lifschitz , Finale Doshi-Velez , Ofra Amir

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This…

Machine Learning · Computer Science 2024-01-30 Burcu Küçükoğlu , Walraaf Borkent , Bodo Rueckauer , Nasir Ahmad , Umut Güçlü , Marcel van Gerven

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that…

In this paper we are introducing a new reinforcement learning method for control problems in environments with delayed feedback. Specifically, our method employs stochastic planning, versus previous methods that used deterministic planning.…

Machine Learning · Computer Science 2024-02-02 Zhiyuan Yao , Ionut Florescu , Chihoon Lee

AlphaZero and its extension MuZero are computer programs that use machine-learning techniques to play at a superhuman level in chess, go, and a few other games. They achieved this level of play solely with reinforcement learning from…

Artificial Intelligence · Computer Science 2022-07-05 Evgeny Dantsin , Vladik Kreinovich , Alexander Wolpert

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally…

Machine Learning · Computer Science 2023-11-09 Tianying Ji , Yu Luo , Fuchun Sun , Mingxuan Jing , Fengxiang He , Wenbing Huang

Despite advancements in deep reinforcement learning algorithms, developing an effective exploration strategy is still an open problem. Most existing exploration strategies either are based on simple heuristics, or require the model of the…

Machine Learning · Computer Science 2021-02-11 Arash Mahyari

We consider the stochastic single node energy storage problem (SNES) and revisit Approximate Policy Iteration (API) to solve SNES. We show that the performance of API can be boosted by using neural networks as an approximation architecture…

Optimization and Control · Mathematics 2019-10-07 Trivikram Dokka , Richlove Frimpong

Methods for learning optimal policies use causal machine learning models to create human-interpretable rules for making choices around the allocation of different policy interventions. However, in realistic policy-making contexts,…

Machine Learning · Computer Science 2023-10-18 Patrick Rehill , Nicholas Biddle

A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or $Q$-function…

Machine Learning · Computer Science 2016-03-01 Joshua Achiam

We introduce a novel reinforcement learning algorithm (AGRO, for Any-Generation Reward Optimization) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies…

Machine Learning · Computer Science 2025-04-01 Yunhao Tang , Taco Cohen , David W. Zhang , Michal Valko , Rémi Munos

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces challenge in continuous control tasks. Conventional methods…

Machine Learning · Computer Science 2020-02-04 Longxiang Shi , Shijian Li , Longbing Cao , Long Yang , Gang Zheng , Gang Pan

State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard to transfer their success to industrial control problems,…

Machine Learning · Computer Science 2021-07-23 Phillip Swazinna , Steffen Udluft , Thomas Runkler

In this paper, a new adaptive multi-batch experience replay scheme is proposed for proximal policy optimization (PPO) for continuous action control. On the contrary to original PPO, the proposed scheme uses the batch samples of past…

Machine Learning · Computer Science 2018-10-03 Seungyul Han , Youngchul Sung

Reinforcement learning (RL) is vital for optimizing large language models (LLMs). Recent Group Relative Policy Optimization (GRPO) estimates advantages using multiple on-policy outputs per prompt, leading to high computational costs and low…

Computation and Language · Computer Science 2025-06-12 Siheng Li , Zhanhui Zhou , Wai Lam , Chao Yang , Chaochao Lu

Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from…

‹ Prev 1 4 5 6 7 8 10 Next ›