Picture for Clare Lyle

Clare Lyle

Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning

Add code
Jul 09, 2024
Viaarxiv icon

Normalization and effective learning rates in reinforcement learning

Add code
Jul 01, 2024
Figure 1 for Normalization and effective learning rates in reinforcement learning
Figure 2 for Normalization and effective learning rates in reinforcement learning
Figure 3 for Normalization and effective learning rates in reinforcement learning
Figure 4 for Normalization and effective learning rates in reinforcement learning
Viaarxiv icon

Weight Clipping for Deep Continual and Reinforcement Learning

Add code
Jul 01, 2024
Viaarxiv icon

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

Add code
Jun 04, 2024
Viaarxiv icon

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

Add code
Jun 01, 2024
Viaarxiv icon

Disentangling the Causes of Plasticity Loss in Neural Networks

Add code
Feb 29, 2024
Figure 1 for Disentangling the Causes of Plasticity Loss in Neural Networks
Figure 2 for Disentangling the Causes of Plasticity Loss in Neural Networks
Figure 3 for Disentangling the Causes of Plasticity Loss in Neural Networks
Figure 4 for Disentangling the Causes of Plasticity Loss in Neural Networks
Viaarxiv icon

Mixtures of Experts Unlock Parameter Scaling for Deep RL

Add code
Feb 13, 2024
Viaarxiv icon

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model

Add code
Feb 12, 2024
Figure 1 for Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Figure 2 for Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Figure 3 for Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Figure 4 for Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Viaarxiv icon

Vision-Language Models as a Source of Rewards

Add code
Dec 14, 2023
Figure 1 for Vision-Language Models as a Source of Rewards
Figure 2 for Vision-Language Models as a Source of Rewards
Figure 3 for Vision-Language Models as a Source of Rewards
Figure 4 for Vision-Language Models as a Source of Rewards
Viaarxiv icon

DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design

Add code
Dec 07, 2023
Figure 1 for DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design
Figure 2 for DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design
Figure 3 for DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design
Figure 4 for DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design
Viaarxiv icon