40 citations · 128 across the 11 of their papers we have counts for
8 papers · 1 filter
Reinforcement Learning with Automated Auxiliary Loss Search
Tairan He, Yuge Zhang, Kan Ren +5
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative…
On the Convergence of Monte Carlo UCB for Random-Length Episodic MDPs
Zixuan Dong, Che Wang, Keith Ross
In reinforcement learning, Monte Carlo algorithms update the Q function by averaging the episodic returns. In the Monte Carlo UCB (MC-UCB) algorithm, the action taken in each state…
Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance
Yanqiu Wu, Xinyue Chen, Che Wang +2
Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks…
Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
Xinyue Chen, Che Wang, Zijian Zhou +1
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 benchma…
On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
Che Wang, Shuhan Yuan, Kai Shao +1
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 t…
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
Xinyue Chen, Zijian Zhou, Zheng Wang +3
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 int…
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
Che Wang, Yanqiu Wu, Quan Vuong +1
We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft…
Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
Che Wang, Keith Ross
Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates w…