Related papers: Modular Adaptive Policy Selection for Multi-Task I…

In this paper, we discuss a framework for teaching bimanual manipulation tasks by imitation. To this end, we present a system and algorithms for learning compliant and contact-rich robot behavior from human demonstrations. The presented…

A common strategy in modern learning systems is to learn a representation that is useful for many tasks, a.k.a. representation learning. We study this strategy in the imitation learning setting for Markov decision processes (MDPs) where…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

The notion that cooperation can aid a group of agents to solve problems more efficiently than if those agents worked in isolation is prevalent, despite the little quantitative groundwork to support it. Here we consider a primordial form of…

Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be…

Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind of imitation…

Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator. This…

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a…

Imitation Learning is a promising paradigm for learning complex robot manipulation skills by reproducing behavior from human demonstrations. However, manipulation tasks often contain bottleneck regions that require a sequence of precise…

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each…

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over…

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously…

Behavioural cloning is an imitation learning technique that teaches an agent how to behave via expert demonstrations. Recent approaches use self-supervision of fully-observable unlabelled snapshots of the states to decode state pairs into…

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each…

Imitation learning has demonstrated strong performance in robotic manipulation by learning from large-scale human demonstrations. While existing models excel at single-task learning, it is observed in practical applications that their…

In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a…

Reinforcement learning algorithms can acquire policies for complex tasks autonomously. However, the number of samples required to learn a diverse set of skills can be prohibitively large. While meta-reinforcement learning methods have…

Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP. However, training or fine-tuning these models for individual tasks can be time consuming and resource intensive. Thus, a lot of…

How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity)…

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…