Exploring Restart Distributions

Abstract

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a more diverse set of initial states, as well as allowing it to restart in states associated with significant past experiences. This approach is compatible with both on-policy and off-policy methods. However, a caveat is that altering the distribution of initial states could change the optimal policies when searching within a restricted class of policies. To reduce this unsought learning bias, we evaluate our approach in deep reinforcement learning which benefits from the high representational capacity of deep neural networks. We instantiate three variants of our approach, each inspired by an idea in the context of experience replay. Using these variants, we show that perform

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytavakoli2018exploring

Related papers

• Curious Explorer: A Provable Exploration Strategy In Policy Learning (2021)0.00
• Replay For Safety (2021)0.00
• Reinforcement Learning With Experience Replay And Adaptation Of Action Dispersion (2022)0.00
• Exploration By Random Distribution Distillation (2025)0.00
• Experience Replay Using Transition Sequences (2017)8.82
• Bag Of Policies For Distributional Deep Exploration (2023)0.00
• Bootstrapping A DQN Replay Memory With Synthetic Experiences (2020)5.84
• CUER: Corrected Uniform Experience Replay For Off-policy Continuous Deep Reinforcement Learning Algorithms (2024)0.00