English
Related papers

Related papers: Backplay: "Man muss immer umkehren"

200 papers

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

Machine Learning · Computer Science 2019-10-24 Aditya Modi , Nan Jiang , Ambuj Tewari , Satinder Singh

The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral…

Machine Learning · Computer Science 2024-06-06 Juntao Ren , Gokul Swamy , Zhiwei Steven Wu , J. Andrew Bagnell , Sanjiban Choudhury

Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to…

Machine Learning · Computer Science 2025-05-12 Renhao Wang , Kevin Frans , Pieter Abbeel , Sergey Levine , Alexei A. Efros

Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet…

Machine Learning · Computer Science 2023-11-22 Marcus Klasson , Hedvig Kjellström , Cheng Zhang

Continual learning seeks to enable machine learning systems to solve an increasing corpus of tasks sequentially. A critical challenge for continual learning is forgetting, where the performance on previously learned tasks decreases as new…

Machine Learning · Computer Science 2025-06-06 Yasaman Mahdaviyeh , James Lucas , Mengye Ren , Andreas S. Tolias , Richard Zemel , Toniann Pitassi

Hindsight Experience Replay (HER) is widely regarded as the state-of-the-art algorithm for achieving sample-efficient multi-goal reinforcement learning (RL) in robotic manipulation tasks with binary rewards. HER facilitates learning from…

Robotics · Computer Science 2025-04-16 Fikrican Özgür , René Zurbrügg , Suryansh Kumar

Simulation is used extensively in autonomous systems, particularly in robotic manipulation. By far, the most common approach is to train a controller in simulation, and then use it as an initial starting point for the real system. We…

Machine Learning · Statistics 2021-10-06 Shirli Di Castro Shashua , Dotan Di Castro , Shie Mannor

Offline Reinforcement Learning (ORL) is a promising approach to reduce the high sample complexity of traditional Reinforcement Learning (RL) by eliminating the need for continuous environmental interactions. ORL exploits a dataset of…

Artificial Intelligence · Computer Science 2024-07-15 Girolamo Macaluso , Alessandro Sestini , Andrew D. Bagdanov

Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a meta-learned addressing model called RAMa that provides…

Machine Learning · Computer Science 2021-10-27 Artem Zholus , Aleksandr I. Panov

In multi-goal reinforcement learning (RL) settings, the reward for each goal is sparse, and located in a small neighborhood of the goal. In large dimension, the probability of reaching a reward vanishes and the agent receives little…

Machine Learning · Computer Science 2021-06-17 Léonard Blier , Yann Ollivier

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Machine Learning · Computer Science 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…

Machine Learning · Computer Science 2019-11-27 Kaixiang Lin , Jiayu Zhou

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this…

Machine Learning · Computer Science 2019-10-16 Kelvin Xu , Ellis Ratner , Anca Dragan , Sergey Levine , Chelsea Finn

Training agents via off-policy deep reinforcement learning (RL) requires a large memory, named replay memory, that stores past experiences used for learning. These experiences are sampled, uniformly or non-uniformly, to create the batches…

Machine Learning · Computer Science 2022-12-27 Bumgeun Park , Taeyoung Kim , Woohyeon Moon , Luiz Felipe Vecchietti , Dongsoo Har

Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to…

Machine Learning · Computer Science 2019-09-24 Bradly C. Stadie , Pieter Abbeel , Ilya Sutskever

Reinforcement learning is a popular method of finding optimal solutions to complex problems. Algorithms like Q-learning excel at learning to solve stochastic problems without a model of their environment. However, they take longer to solve…

Artificial Intelligence · Computer Science 2024-04-25 Jan Diekhoff , Jörn Fischer

Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…

Machine Learning · Computer Science 2022-12-16 Mark A. Rucker , Layne T. Watson , Matthew S. Gerber , Laura E. Barnes

Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and…

Machine Learning · Computer Science 2019-04-12 Bilal Kartal , Pablo Hernandez-Leal , Chao Gao , Matthew E. Taylor