Search Results for author:
Found 17 papers, 8 papers with code
Vision-Language Models as a Source of Rewards
Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning.
Acceleration in Policy Optimization
We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates.
Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution.
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
Such applications often require to put constraints on the agent's behavior.
Discovering Evolution Strategies via Meta-Black-Box Optimization
Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies.
Probing Transfer in Deep Reinforcement Learning without Task Engineering
By formally organising these modifications into several factors of variation, we are able to show that Analyses of Variance (ANOVA) are a potent tool for studying the effects of human-relevant domain changes on the learning and transfer performance of a deep reinforcement learning agent.
Meta-Gradients in Non-Stationary Environments
We support these results with a qualitative analysis of resulting meta-parameter schedules and learned functions of context features.
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations.
Introducing Symmetries to Black Box Meta Reinforcement Learning
We show that a recent successful meta RL approach that meta-learns an objective for backpropagation-based learning exhibits certain symmetries (specifically the reuse of the learning rule, and invariance to input and output permutations) that are not present in typical black-box meta RL systems.
Bootstrapped Meta-Learning
We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark and demonstrate that it yields both performance and efficiency gains in multi-task meta-learning.
Discovering Diverse Nearly Optimal Policies with Successor Features
We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features, while assuring that they are near optimal.
Temporal Difference Uncertainties as a Signal for Exploration
Instead, we incorporate it as an intrinsic reward and treat exploration as a separate learning problem, induced by the agent's temporal difference uncertainties.
QuantNet: Transferring Learning Across Systematic Trading Strategies
The encoder transforms market-specific data into an abstract latent representation that is processed by a global model shared by all markets, while the decoder learns a market-specific trading strategy based on both local and global information from the market-specific encoder and the global model.
Meta-Learning with Warped Gradient Descent
On the other hand, approaches that try to control a gradient-based update rule typically resort to computing gradients through the learning process to obtain their meta-gradients, leading to methods that can not scale beyond few-shot task adaptation.
Augmenting correlation structures in spatial data using deep generative models
We empirically show the superiority of this approach over conventional ensemble learning approaches and rivaling spatial data augmentation methods, using synthetic and real-world prediction tasks.
Transferring Knowledge across Learning Processes
Approaches that transfer information contained only in the final parameters of a source model will therefore struggle.
Breaking the Activation Function Bottleneck through Adaptive Parameterization
Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large.
