Search Results for author:
Found 13 papers, 7 papers with code
Compound Returns Reduce Variance in Reinforcement Learning
Multistep returns, such as $n$-step returns and $\lambda$-returns, are commonly used to improve the sample efficiency of reinforcement learning (RL) methods.
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging.
Adaptive Tree Backup Algorithms for Temporal-Difference Reinforcement Learning
Q($\sigma$) is a recently proposed temporal-difference learning method that interpolates between learning from expected backups and sampled backups.
Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting for Past Decisions
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks.
Virtual Replay Cache
Return caching is a recent strategy that enables efficient minibatch training with multistep estimators (e. g. the {\lambda}-return) for deep reinforcement learning.
Human-Level Control without Server-Grade Hardware
Deep Q-Network (DQN) marked a major milestone for reinforcement learning, demonstrating for the first time that human-level control policies could be learned directly from raw visual inputs via reward maximization.
Investigating Alternatives to the Root Mean Square for Adaptive Gradient Methods
Adam is an adaptive gradient method that has experienced widespread adoption due to its fast and reliable training performance.
Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning
Our theory prescribes a special non-uniform distribution to cancel this effect, and we propose a stratified sampling scheme to efficiently implement it.
Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning
Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community.
Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability
Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state.
Expectigrad: Fast Stochastic Optimization with Robust Convergence Properties
Many popular adaptive gradient methods such as Adam and RMSProp rely on an exponential moving average (EMA) to normalize their stepsizes.
Reconciling λ-Returns with Experience Replay
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the λ-return difficult in this context.
Reconciling $λ$-Returns with Experience Replay
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context.
