48 citations · 227 across the 26 of their papers we have counts for
7 papers · 1 filter
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance
Michael Luo, Ashwin Balakrishna, Brijen Thananjeyan +6
Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating const…
LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks
Albert Wilcox, Ashwin Balakrishna, Brijen Thananjeyan +2
Reinforcement learning (RL) has shown impressive success in exploring high-dimensional environments to learn complex tasks, but can often exhibit unsafe behaviors and require exten…
PAC Best Arm Identification Under a Deadline
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica +3
We study -PAC best arm identification, where a decision-maker must identify an -optimal arm with probability at least , while minimizing the number of arm pulls (…
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica +3
We study exploration in stochastic multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on…
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair +7
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety require…
On-Policy Robot Imitation Learning from a Converging Supervisor
Ashwin Balakrishna, Brijen Thananjeyan, Jonathan Lee +4
Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during polic…
Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia +6
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncert…