Learning Efficient And Effective Exploration Policies With Counterfactual Meta Policy

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2019learning

Related papers

• Decoupling Exploration And Exploitation For Meta-reinforcement Learning Without Sacrifices (2020)0.00
• Multi-path Policy Optimization (2019)0.00
• First-explore, Then Exploit: Meta-learning To Solve Hard Exploration-exploitation Trade-offs (2023)0.00
• Learning To Explore With Meta-policy Gradient (2018)0.00
• Centralized Cooperative Exploration Policy For Continuous Control Tasks (2023)0.00
• Conservative Exploration For Policy Optimization Via Off-policy Policy Evaluation (2023)0.00
• Meta Reinforcement Learning With Distribution Of Exploration Parameters Learned By Evolution Strategies (2018)0.00
• Exploration Conscious Reinforcement Learning Revisited (2018)0.00