Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy
A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for exploration involve task-agnostic design, that is performing well in one environment, but be ill-suited to another. To the purpose of learning an effective and efficient exploration policy in an automated manner. We formalized a feasible metric for measuring the utility of exploration based on counterfactual ideology. Based on that, We proposed an end-to-end algorithm to learn exploration policy by meta-learning. We demonstrate that our method achieves good results compared to previous works in the high-dimensional control tasks in MuJoCo simulator.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualEfficient ExplorationMeta-LearningMuJoCoReinforcement LearningSimilar Papers 제목 키워드 기반
Learning Exploration Policies for Model-Agnostic Meta-Reinforcement Learning
Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding …
Efficient ExplorationMeta Reinforcement Learningreinforcement-learningReinforcement Learning+1MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward t…
Efficient ExplorationMeta Reinforcement LearningMuJoCoreinforcement-learning+2Differentiable Meta-Learning of Bandit Policies
Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution P. In this work, we learn such policies for an unknown distribution P using samples from P. Our app…
Meta-LearningConservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are…
MAME : Model-Agnostic Meta-Exploration
Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding …
Efficient ExplorationMeta Reinforcement LearningmodelReinforcement Learning