1 citations · 2 across the 12 of their papers we have counts for
12 papers · 1 filter
Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion
Arthur Louette, Alejandro Sánchez Roncero, Gaspard Lambrechts +4
In partially observable Markov decision processes, the optimal policy generally depends on the history of observations and past actions. Asymmetric actor-critic methods have become…
Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance
Gaspard Lambrechts, Adrien Bolland, Daniel Ebi +1
Much like humans benefit from guidance while learning, reinforcement learning algorithms may benefit from additional supervision beyond rewards. Leveraging additional information d…
Maximum-Entropy Exploration with Future State-Action Visitation Measures
Adrien Bolland, Gaspard Lambrechts, Damien Ernst
Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewa…
Parallelizable memory recurrent units
Florent De Geeter, Gaspard Lambrechts, Damien Ernst +1
With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of seq…
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
Daniel Ebi, Damien Ernst, Klemens Böhm +1
Asymmetric reinforcement learning leverages privileged information available during training to improve learning under partial observability. Existing asymmetric actor-critic metho…
A Theoretical Justification for Asymmetric Actor-Critic Algorithms
Gaspard Lambrechts, Damien Ernst, Aditya Mahajan
In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages add…
Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures
Adrien Bolland, Gaspard Lambrechts, Damien Ernst
Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In th…
Parallelizing Autoregressive Generation with Variational State Space Models
Gaspard Lambrechts, Yann Claes, Pierre Geurts +1
Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although bo…
Behind the Myth of Exploration in Policy Gradients
Adrien Bolland, Gaspard Lambrechts, Damien Ernst
In order to compute near-optimal policies with policy-gradient algorithms, it is common in practice to include intrinsic exploration terms in the learning objective. Although the e…
Informed POMDP: Leveraging Additional Information in Model-Based RL
Gaspard Lambrechts, Adrien Bolland, Damien Ernst
In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce…
Recurrent networks, hidden states and beliefs in partially observable environments
Gaspard Lambrechts, Adrien Bolland, Damien Ernst
Reinforcement learning aims to learn optimal policies from interaction with environments whose dynamics are unknown. Many methods rely on the approximation of a value function to d…
Warming up recurrent neural networks to maximise reachable multistability greatly improves learning
Gaspard Lambrechts, Florent De Geeter, Nicolas Vecoven +2
Training recurrent neural networks is known to be difficult when time dependencies become long. In this work, we show that most standard cells only have one stable equilibrium at i…