Search Results for author:
Found 15 papers, 0 papers with code
Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks
Under PA, operators perform manual operations (providing actions) and operations that switch to automatic/manual mode (mode-switching).
Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly.
Physically Consistent Preferential Bayesian Optimization for Food Arrangement
To cope with this problem, we propose Physically Consistent Preferential Bayesian Optimization (PCPBO) as a method that obtains physically feasible and preferred arrangements that satisfy domain rules.
Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization
Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to the real world in a zero-shot setting.
Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation
However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a significant human effort in transferring the models learned in simulations to new domains in the real world.
$q$-Munchausen Reinforcement Learning
The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy.
Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning
Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy.
AdaTerm: Adaptive T-Distribution Estimated Robust Moments towards Noise-Robust Stochastic Gradient Optimizer
As a safety net, it is natural to improve the robustness to noise of the optimization algorithm which updates the network parameters in the final process of learning.
Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning
The recent boom in the literature on entropy-regularized reinforcement learning (RL) approaches reveals that Kullback-Leibler (KL) regularization brings advantages to RL algorithms by canceling out errors under mild assumptions.
Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning
In this paper, we propose cautious policy programming (CPP), a novel value-based reinforcement learning (RL) algorithm that can ensure monotonic policy improvement during learning.
Cautious Actor-Critic
The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better.
Deep reinforcement learning of event-triggered communication and control for multi-agent cooperative transport
In this paper, we explore a multi-agent reinforcement learning approach to address the design problem of communication and control strategies for multi-agent cooperative transport.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Uncertainty-aware Contact-safe Model-based Reinforcement Learning
In typical MBRL, we cannot expect the data-driven model to generate accurate and reliable policies to the intended robotic tasks during the learning process due to sample scarcity.
Model-based Reinforcement Learning
reinforcement-learning
+1
Ensuring Monotonic Policy Improvement in Entropy-regularized Value-based Reinforcement Learning
We propose a novel reinforcement learning algorithm that exploits this lower-bound as a criterion for adjusting the degree of a policy update for alleviating policy oscillation.
Learning Force Control for Contact-rich Manipulation Tasks with Rigid Position-controlled Robots
Thirdly, we developed a fail-safe mechanism for safely training an RL agent on manipulation tasks using a real rigid robot manipulator.
