Search Results for author:
Found 11 papers, 5 papers with code
Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
We first show empirically that models trained with label smoothing converge faster to neural collapse solutions and attain a stronger level of neural collapse.
Pre-training with Synthetic Data Helps Offline Reinforcement Learning
Recently, it has been shown that for offline deep reinforcement learning (DRL), pre-training Decision Transformer with a large language corpus can improve downstream performance (Reid et al., 2022).
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs
We nevertheless show that for a large class of MDPs, which includes stochastic MDPs such as blackjack and deterministic MDPs such as Go, the Q-function in MC-UCB converges almost surely to the optimal Q function.
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks.
Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks.
On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function.
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment.
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic.
Multi-task Batch Reinforcement Learning with Metric Learning
To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards.
Towards Simplicity in Deep Reinforcement Learning: Streamlined Off-Policy Learning
The field of Deep Reinforcement Learning (DRL) has recently seen a surge in the popularity of maximum entropy reinforcement learning algorithms.
Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
The ERE algorithm samples more aggressively from recent experience, and also orders the updates to ensure that updates from old data do not overwrite updates from new data.
