Search Results for author:
Found 23 papers, 7 papers with code
Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist
This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one.
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
We study a primal-dual reinforcement learning (RL) algorithm for the online constrained Markov decision processes (CMDP) problem, wherein the agent explores an optimal policy that maximizes return while satisfying constraints.
Local and adaptive mirror descents in extensive-form games
We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback.
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings.
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performing practical RL algorithms.
Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints
This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms.
Robust Markov Decision Processes without Model Estimation
Moreover, we prove the alternative form still plays a similar role as the original form.
Adapting to game trees in zero-sum imperfect information games
Imperfect information games (IIG) are games in which each player only partially observes the current game state.
Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$-realizable MDPs
Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $\epsilon$ of the action-value functions of stationary policies.
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
In this work, we consider and analyze the sample complexity of model-free reinforcement learning with a generative model.
No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
The performance of reinforcement learning (RL) agents is sensitive to the choice of hyperparameters.
Learning in two-player zero-sum partially observable Markov games with perfect recall
We study the problem of learning a Nash equilibrium (NE) in an extensive game with imperfect information (EGII) through self-play.
Variational oracle guiding for reinforcement learning
How to make intelligent decisions is a central problem in machine learning and cognitive science.
Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences
Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification.
Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation
Model-agnostic meta-reinforcement learning requires estimating the Hessian matrix of value functions.
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play.
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning
These results show which implementation or code details are co-adapted and co-evolved with algorithms, and which are transferable across algorithms: as examples, we identified that tanh Gaussian policy and network sizes are highly adapted to algorithmic types, while layer normalization and ELU are critical for MPO's performances but also transfer to noticeable gains in SAC.
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments.
Revisiting Peng's Q($λ$) for Modern Reinforcement Learning
These results indicate that Peng's Q($\lambda$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning
Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance.
Leverage the Average: an Analysis of KL Regularization in RL
Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance.
Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning
We provide detailed theoretical analysis of the new algorithm that shows its efficiency and noise-tolerance inherited from Retrace and advantage learning.
Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming
Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks.
