Search Results for author:
Found 5 papers, 2 papers with code
A Case for Validation Buffer in Pessimistic Actor-Critic
VPL uses a small validation buffer to adjust the levels of pessimism throughout the agent training, with the pessimism set such that the approximation error of the critic targets is minimized.
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
We tested these agents across 14 diverse tasks from 2 simulation benchmarks.
On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics
Risk-aware Reinforcement Learning (RL) algorithms like SAC and TD3 were shown empirically to outperform their risk-neutral counterparts in a variety of continuous-action tasks.
On Many-Actions Policy Gradient
We study the variance of stochastic policy gradients (SPGs) with many action samples per state.
Low-Variance Policy Gradient Estimation with World Models
In WMPG, a WM is trained online and used to imagine trajectories.
