CoachNet: An Adversarial Sampling Approach for Reinforcement Learning

2021-01-07 · Elmira Amirloo Abolfathi, Jun Luo, Peyman Yadmellat, Kasra Rezaee

Despite the recent successes of reinforcement learning in games and robotics, it is yet to become broadly practical. Sample efficiency and unreliable performance in rare but challenging scenarios are two of the major obstacles. Drawing inspiration from the effectiveness of deliberate practice for achieving expert-level human performance, we propose a new adversarial sampling approach guided by a failure predictor named "CoachNet". CoachNet is trained online along with the agent to predict the probability of failure. This probability is then used in a stochastic sampling process to guide the agent to more challenging episodes. This way, instead of wasting time on scenarios that the agent has already mastered, training is focused on the agent's "weak spots". We present the design of CoachNet, explain its underlying principles, and empirically demonstrate its effectiveness in improving sample efficiency and test-time robustness in common continuous control tasks.

📄 PDF Abstract BibTeX arXiv:2101.02649

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-control Continuous Control reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Discriminator Soft Actor Critic without Extrinsic Rewards

2020-01-19 · Daichi Nishio, Daiki Kuyoshi, Toi Tsuneda, Satoshi Yamane

It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer f…

Imitation Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

2023-10-30 · NeurIPS 2023 11

This paper investigates posterior sampling algorithms for competitive reinforcement learning (RL) in the context of general function approximations. Focusing on zero-sum Markov games (MGs) under two critical settings, na…

Reinforcement Learning (RL)

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation

2025-03-26 · Hongye Cao, Fan Feng, Jing Huo, Shangdong Yang 외

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble mo…

D4RL Data Augmentation Offline RL reinforcement-learning+2

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

2020-02-14 · Parameswaran Kamalaruban, Yu-Ting Huang, Ya-Ping Hsieh, Paul Rolland 외

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-pl…

MuJoCo reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator

2024-01-30 · Ryoma Furuyama, Daiki Kuyoshi, Satoshi Yamane

Imitation learning is often used in addition to reinforcement learning in environments where reward design is difficult or where the reward is sparse, but it is difficult to be able to imitate well in unknown states from…

Imitation Learning MuJoCo Q-Learning reinforcement-learning+1