research
∙
08/07/2023
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
StarCraft II is one of the most challenging simulated reinforcement lear...
share
research
∙
08/02/2023
Direct Gradient Temporal Difference Learning
Off-policy learning enables a reinforcement learning (RL) agent to reaso...
research
∙
01/31/2023
Improving Monte Carlo Evaluation with Offline Data
Monte Carlo (MC) methods are the most widely used methods to estimate th...
research
∙
02/14/2022
On the Chattering of SARSA with Linear Function Approximation
SARSA, a classical on-policy control algorithm for reinforcement learnin...
research
∙
11/04/2021
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
In this paper, we establish the global optimality and convergence rate o...
research
∙
08/11/2021
Truncated Emphatic Temporal Difference Methods for Prediction and Control
Emphatic Temporal Difference (TD) methods are a class of off-policy Rein...
research
∙
07/12/2021
Learning Expected Emphatic Traces for Deep RL
Off-policy sampling and experience replay are key for improving sample e...
research
∙
01/21/2021
Breaking the Deadly Triad with a Target Network
The deadly triad refers to the instability of a reinforcement learning a...
research
∙
01/08/2021
Average-Reward Off-Policy Policy Evaluation with Function Approximation
We consider off-policy policy evaluation with function approximation (FA...
research
∙
10/02/2020
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
We investigate the discounting mismatch in actor-critic algorithm implem...
research
∙
07/09/2020
Learning Retrospective Knowledge with Reverse Reinforcement Learning
We present a Reverse Reinforcement Learning (Reverse RL) approach for re...
research
∙
04/22/2020
Per-Step Reward: A New Perspective for Risk-Averse Reinforcement Learning
We present a new per-step reward perspective for risk-averse control in ...
research
∙
01/29/2020
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
We present GradientDICE for estimating the density ratio between the sta...
research
∙
11/11/2019
Provably Convergent Off-Policy Actor-Critic with Function Approximation
We present the first provably convergent off-policy actor-critic algorit...
research
∙
05/13/2019
Distributional Reinforcement Learning for Efficient Exploration
In distributional reinforcement learning (RL), the estimated distributio...
research
∙
05/12/2019
Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards
Intrinsic rewards are introduced to simulate how human intelligence work...
research
∙
05/03/2019
Deep Residual Reinforcement Learning
We revisit residual algorithms in both model-free and model-based reinfo...
research
∙
04/29/2019
DAC: The Double Actor-Critic Architecture for Learning Options
We reformulate the option framework as two parallel augmented MDPs. Unde...
research
∙
03/27/2019
Generalized Off-Policy Actor-Critic
We propose a new objective, the counterfactual objective, unifying exist...
research
∙
11/06/2018
ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
In this paper, we propose an actor ensemble algorithm, named ACE, for co...
research
∙
11/05/2018
QUOTA: The Quantile Option Architecture for Reinforcement Learning
In this paper, we propose the Quantile Option Architecture (QUOTA) for e...
research
∙
12/04/2017
A Deeper Look at Experience Replay
Experience replay plays an important role in the success of deep reinfor...
research
∙
11/30/2017
Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control
Reinforcement learning and evolutionary strategy are two major approache...
research
∙
12/09/2016