Search Results for author:
Found 10 papers, 2 papers with code
PASTA: Pretrained Action-State Transformer Agents
Self-supervised learning has brought about a revolutionary paradigm shift in various computing domains, including NLP, vision, and biology.
Model-based Offline Reinforcement Learning with Local Misspecification
We present a model-based offline reinforcement learning policy performance lower bound that explicitly captures dynamics model misspecification and distribution mismatch and we propose an empirical algorithm for optimal offline policy selection.
Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data
Inspired by statistical model selection methods for supervised learning, we introduce a task- and method-agnostic pipeline for automatically training, comparing, selecting, and deploying the best policy when the provided dataset is limited in size.
Offline Policy Optimization with Eligible Actions
Offline policy optimization could have a large impact on many real-world decision-making problems, as online learning may be infeasible in many applications.
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics
In SAAC, the adversary aims to break the safety constraint while the RL agent aims to maximize the constrained value function given the adversary's policy.
Adversarially Guided Actor-Critic
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck.
Learning Value Functions in Deep Policy Gradients using Residual Variance
We prove the theoretical consistency of the new gradient estimator and observe dramatic empirical improvement across a variety of continuous control tasks and algorithms.
MERL: Multi-Head Reinforcement Learning
In this paper: (a) We introduce and define MERL, the multi-head reinforcement learning framework we use throughout this work.
Samples Are Useful? Not Always: denoising policy gradient updates using variance explained
In this work, Vex is used to evaluate the impact each transition will have on learning: this criterion refines sampling and improves the policy gradient algorithm.
Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL
In this work, we use this metric to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods.
