Search Results for author:
Found 16 papers, 2 papers with code
Bootstrapped Representations in Reinforcement Learning
In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988).
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings.
An Analysis of Quantile Temporal-Difference Learning
We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning.
Distributional Reinforcement Learning
reinforcement-learning
+1
On the Expressivity of Markov Reward
We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists.
Model-Free Counterfactual Credit Assignment
Credit assignment in reinforcement learning is the problem of measuring an action’s influence on future rewards.
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards.
Useful Policy Invariant Shaping from Arbitrary Advice
Furthermore, if the reward is constructed from a potential function, the optimal policy is guaranteed to be unaltered.
Hindsight Credit Assignment
We consider the problem of efficient credit assignment in reinforcement learning.
Conditional Importance Sampling for Off-Policy Learning
We theoretically analyse this space, and concretely investigate several algorithms that arise from this framework.
The Termination Critic
In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents.
Learning with Options that Terminate Off-Policy
Generally, learning with longer options (like learning with multi-step returns) is known to be more efficient.
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability.
Safe and Efficient Off-Policy Reinforcement Learning
In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning.
Q($λ$) with Off-Policy Corrections
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities.
Off-Policy Reward Shaping with Ensembles
While PBRS is proven to always preserve optimal policies, its effect on learning speed is determined by the quality of its potential function, which, in turn, depends on both the underlying heuristic and the scale.
Off-Policy Shaping Ensembles in Reinforcement Learning
Recent advances of gradient temporal-difference methods allow to learn off-policy multiple value functions in parallel with- out sacrificing convergence guarantees or computational efficiency.
