Imitating Unknown Policies via Exploration

2020-08-13 · Nathan Gavenski, Juarez Monteiro, Roger Granada, Felipe Meneguzzi, Rodrigo C. Barros

Behavioral cloning is an imitation learning technique that teaches an agent how to behave through expert demonstrations. Recent approaches use self-supervision of fully-observable unlabeled snapshots of the states to decode state-pairs into actions. However, the iterative learning scheme from these techniques are prone to getting stuck into bad local minima. We address these limitations incorporating a two-phase model into the original framework, which learns from unlabeled observations via exploration, substantially improving traditional behavioral cloning by exploiting (i) a sampling mechanism to prevent bad local minima, (ii) a sampling mechanism to improve exploration, and (iii) self-attention modules to capture global features. The resulting technique outperforms the previous state-of-the-art in four different environments by a large margin.

📄 PDF Abstract BibTeX arXiv:2008.05660

Code (2)

NathanGavenski/IUPE 공식 구현 pytorch

nathangavenski/il-datasets pytorch

Tasks

Behavioural cloningImitation Learning

Robust Asymmetric Learning in POMDPs

2020-12-31 · Andrew Warrington, J. Wilder Lavington, Adam Ścibior, Mark Schmidt 외

Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind …

Imitation Learning

Error Bounds of Imitating Policies and Environments

2020-10-22 · NeurIPS 2020 12 · Tian Xu, Ziniu Li, Yang Yu

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, w…

Imitation Learning Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Match or Replay: Self Imitating Proximal Policy Optimization

2026-03-29 · Gaurav Chaudhary, Laxmidhar Behera, Washim Uddin Mondal arxiv

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance be…

Reinforcement Learning

Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments

2021-05-04 · Ashley Peake, Joe McCalmon, Yixin Zhang, Daniel Myers 외

Performing autonomous exploration is essential for unmanned aerial vehicles (UAVs) operating in unknown environments. Often, these missions start with building a map for the environment via pure exploration and subsequen…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications

2023-11-28 · Jun Wang, Hosein Hasanbeig, Kaiyuan Tan, Zihe Sun 외

This paper addresses the problem of designing optimal control policies for mobile robots with mission and safety requirements specified using Linear Temporal Logic (LTL). We consider robots with unknown stochastic dynami…

Deep Reinforcement Learning Robot Navigation