Related papers: Planning with RL and episodic-memory behavioral pr…
Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories. Such method follows the supervised learning paradigm and it strongly…
Reinforcement Learning (RL) has shown remarkable progress in simulation environments, yet its application to real-world robotic tasks remains limited due to challenges in exploration and generalization. To address these issues, we introduce…
Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put…
Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and…
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well. To address this "cold start" problem, we propose a novel approach of using cognitive models to…
Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a…
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…
Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help…
This paper proposes an exploration-efficient Deep Reinforcement Learning with Reference policy (DRLR) framework for learning robotics tasks that incorporates demonstrations. The DRLR framework is developed based on an algorithm called…
Deep reinforcement learning (RL) agents are able to learn contact-rich manipulation tasks by maximizing a reward signal, but require large amounts of experience, especially in environments with many obstacles that complicate exploration. In…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…
Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents…
Interaction-aware planning for autonomous driving requires an exploration of a combinatorial solution space when using conventional search- or optimization-based motion planners. With Deep Reinforcement Learning, optimal driving strategies…
Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable…
Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. Such methods enable agents to learn complex tasks from humans that are…
Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…
We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…