Inverse reinforcement learning from failure

Inverse reinforcement learning from failure

<em>Inverse reinforcement learning</em> (IRL) allows autonomous agents to learn to solve complex tasks from successful demonstrations. However, in many settings, e.g., when a human learns the task by trial and error, <em>failed</em> demonstrations are also readily available....

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς:	Shiarlis, K, Messias, J, Whiteson, S
Μορφή:	Conference item
Έκδοση:	International Foundation for Autonomous Agents and Multiagent Systems 2016

Παρόμοια τεκμήρια

Rapidly exploring learning trees
ανά: Shiarlis, K, κ.ά.
Έκδοση: (2017)

Learning from demonstration in the wild
ανά: Behbahani, F, κ.ά.
Έκδοση: (2019)

Identifiability in inverse reinforcement learning
ανά: Cao, H, κ.ά.
Έκδοση: (2021)

Bayesian Nonparametric Inverse Reinforcement Learning
ανά: How, Jonathan P., κ.ά.
Έκδοση: (2013)

TACO: Learning task decomposition via temporal alignment for control
ανά: Shiarlis, K, κ.ά.
Έκδοση: (2018)

Dynamic-depth context tree weighting
ανά: Messias, J, κ.ά.
Έκδοση: (2018)

Trust-region inverse reinforcement learning
ανά: Cao, Kun, κ.ά.
Έκδοση: (2023)

Improving the efficiency of Bayesian inverse reinforcement learning
ανά: How, Jonathan P., κ.ά.
Έκδοση: (2013)

A survey of inverse reinforcement learning techniques
ανά: Shao, Zhifei, κ.ά.
Έκδοση: (2013)

OFFER: Off-environment reinforcement learning
ανά: Ciosek, K, κ.ά.
Έκδοση: (2017)

Expected policy gradients for reinforcement learning
ανά: Ciosek, K, κ.ά.
Έκδοση: (2020)

Deep residual reinforcement learning
ανά: Zhang, S, κ.ά.
Έκδοση: (2020)

Learning retrospective knowledge with reverse reinforcement learning
ανά: Zhang, S, κ.ά.
Έκδοση: (2020)

Inverse reinforcement learning with locally consistent reward functions
ανά: Nguyen, Quoc Phong, κ.ά.
Έκδοση: (2018)

Deep reinforcement learning for intractable routing & inverse problems
ανά: Zhang, Rongkai
Έκδοση: (2023)

Bayesian action decoder for deep multi-agent reinforcement learning
ανά: Whiteson, S
Έκδοση: (2019)

VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
ανά: Zintgraf, L, κ.ά.
Έκδοση: (2020)

A review of inverse reinforcement learning theory and recent advances
ανά: Shao, Zhifei, κ.ά.
Έκδοση: (2013)

Fingerprint policy optimisation for robust reinforcement learning
ανά: Paul, S, κ.ά.
Έκδοση: (2019)

Learning to communicate with Deep multi-agent reinforcement learning
ανά: Foerster, J, κ.ά.
Έκδοση: (2016)

Deep variational reinforcement learning for POMDPs
ανά: Igl, M, κ.ά.
Έκδοση: (2018)

Robust reinforcement learning with Bayesian optimisation and quadrature
ανά: Paul, S, κ.ά.
Έκδοση: (2020)

Mean−variance policy iteration for risk−averse reinforcement learning
ανά: Zhang, S, κ.ά.
Έκδοση: (2021)

VIREL: A variational inference framework for reinforcement learning
ανά: Fellows, M, κ.ά.
Έκδοση: (2019)

Large-scale cost function learning for path planning using deep inverse reinforcement learning
ανά: Wulfmeier, M, κ.ά.
Έκδοση: (2017)

Transient non−stationarity and generalisation in deep reinforcement learning
ανά: Igl, M, κ.ά.
Έκδοση: (2021)

Multi-agent common knowledge reinforcement learning
ανά: de Witt, C, κ.ά.
Έκδοση: (2019)

Space Objects Maneuvering Prediction via Maximum Causal Entropy Inverse Reinforcement Learning
ανά: Doerr, Bryce G, κ.ά.
Έκδοση: (2021)

Game-theoretic inverse reinforcement learning: a differential pontryagin's maximum principle approach
ανά: Cao, Kun, κ.ά.
Έκδοση: (2022)

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
ανά: Castellini, J, κ.ά.
Έκδοση: (2021)

TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
ανά: Farquhar, G, κ.ά.
Έκδοση: (2018)

Learning programs by learning from failures
ανά: Cropper, A, κ.ά.
Έκδοση: (2021)

A survey of reinforcement learning informed by natural language
ανά: Luketina, J, κ.ά.
Έκδοση: (2019)

Reinforcement learning enhanced quantum-inspired algorithm for combinatorial optimization
ανά: Beloborodov, D, κ.ά.
Έκδοση: (2020)

Exploration in approximate hyper-state space for meta reinforcement learning
ανά: Zintgraf, L, κ.ά.
Έκδοση: (2021)

Stabilising experience replay for deep multi-agent reinforcement learning
ανά: Foerster, J, κ.ά.
Έκδοση: (2017)

UneVEn: Universal value exploration for multi-agent reinforcement learning
ανά: Gupta, T, κ.ά.
Έκδοση: (2021)

Splitting failure of reinforced concrete columns
ανά: Pham, Thanh Phuong, κ.ά.
Έκδοση: (2013)

Randomized entity-wise factorization for multi-agent reinforcement learning
ανά: Iqbal, S, κ.ά.
Έκδοση: (2021)

Loaded DiCE: Trading off bias and variance in any-order score function gradient estimators for reinforcement learning
ανά: Farquhar, G, κ.ά.
Έκδοση: (2019)