Ignasi Clavera
YOU?
Author Swipe
View article: Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning Open
Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a generalizable dynamics model robust to changes in dynamics remains a c…
View article: Trajectory-wise Multiple Choice Learning for Dynamics Generalization in\n Reinforcement Learning
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in\n Reinforcement Learning Open
Model-based reinforcement learning (RL) has shown great potential in various\ncontrol tasks in terms of both sample-efficiency and final performance.\nHowever, learning a generalizable dynamics model robust to changes in dynamics\nremains …
View article: Model-Augmented Actor-Critic: Backpropagating through Paths
Model-Augmented Actor-Critic: Backpropagating through Paths Open
Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of th…
View article: Mutual Information Maximization for Robust Plannable Representations
Mutual Information Maximization for Robust Plannable Representations Open
Extending the capabilities of robotics to real-world complex, unstructured environments requires the need of developing better perception systems while maintaining low sample complexity. When dealing with high-dimensional state spaces, cur…
View article: Model-Augmented Actor-Critic: Backpropagating through Paths
Model-Augmented Actor-Critic: Backpropagating through Paths Open
Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of th…
View article: Asynchronous Methods for Model-Based Reinforcement Learning
Asynchronous Methods for Model-Based Reinforcement Learning Open
Significant progress has been made in the area of model-based reinforcement learning. State-of-the-art algorithms are now able to match the asymptotic performance of model-free methods while being significantly more data efficient. However…
View article: Asynchronous Methods for Model-Based Reinforcement Learning.
Asynchronous Methods for Model-Based Reinforcement Learning. Open
Significant progress has been made in the area of model-based reinforcement learning. State-of-the-art algorithms are now able to match the asymptotic performance of model-free methods while being significantly more data efficient. However…
View article: Benchmarking Model-Based Reinforcement Learning
Benchmarking Model-Based Reinforcement Learning Open
Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for auth…
View article: Sub-policy Adaptation for Hierarchical Reinforcement Learning
Sub-policy Adaptation for Hierarchical Reinforcement Learning Open
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a hig…
View article: ProMP: Proximal Meta-Policy Search
ProMP: Proximal Meta-Policy Search Open
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-t…
View article: Model-Based Reinforcement Learning via Meta-Policy Optimization
Model-Based Reinforcement Learning via Meta-Policy Optimization Open
Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic p…
View article: Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning Open
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause profic…
View article: Learning to Adapt: Meta-Learning for Model-Based Control
Learning to Adapt: Meta-Learning for Model-Based Control Open
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations can cause proficient but narrowly…
View article: Learning to Adapt in Dynamic, Real-World Environments Through\n Meta-Reinforcement Learning
Learning to Adapt in Dynamic, Real-World Environments Through\n Meta-Reinforcement Learning Open
Although reinforcement learning methods can achieve impressive results in\nsimulation, the real world presents two major challenges: generating samples is\nexceedingly expensive, and unexpected perturbations or unseen situations cause\npro…
View article: Model-Ensemble Trust-Region Policy Optimization
Model-Ensemble Trust-Region Policy Optimization Open
Model-free reinforcement learning (RL) methods are succeeding in a growing number of tasks, aided by recent advances in deep learning. However, they tend to suffer from high sample complexity, which hinders their use in real-world domains.…
View article: Model-Ensemble Trust-Region Policy Optimization
Model-Ensemble Trust-Region Policy Optimization Open
Model-free reinforcement learning (RL) methods are succeeding in a growing number of tasks, aided by recent advances in deep learning. However, they tend to suffer from high sample complexity, which hinders their use in real-world domains.…