Manipulating The Distributions Of Experience Used For Self-play Learning In Expert Iteration

Abstract

Expert Iteration (ExIt) is an effective framework for learning game-playing policies from self-play. ExIt involves training a policy to mimic the search behaviour of a tree search algorithm - such as Monte-Carlo tree search - and using the trained policy to guide it. The policy and the tree search can then iteratively improve each other, through experience gathered in self-play between instances of the guided tree search algorithm. This paper outlines three different approaches for manipulating the distribution of data collected from self-play, and the procedure that samples batches for learning updates from the collected data. Firstly, samples in batches are weighted based on the durations of the episodes in which they were originally experienced. Secondly, Prioritized Experience Replay is applied within the ExIt framework, to prioritise sampling experience from which we expect to obtain valuable training signals. Thirdly, a trained exploratory policy is used to diversify the trajecto

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysoemers2020manipulating

Related papers

• Adapting Behaviour For Learning Progress (2019)0.00
• Which Experiences Are Influential For Your Agent? Policy Iteration With Turn-over Dropout (2023)0.00
• Experience Replay Using Transition Sequences (2017)8.82
• Brexit: On Opponent Modelling In Expert Iteration (2022)0.00
• Reinforcement Learning With Experience Replay And Adaptation Of Action Dispersion (2022)0.00
• Learning Policies From Self-play With Policy Gradients And MCTS Value Estimates (2019)0.00
• Which Experiences Are Influential For RL Agents? Efficiently Estimating The Influence Of Experiences (2024)0.00
• Adaptive Experience Selection For Policy Gradient (2020)0.00