Trust Region Policy Optimization
read the original abstract
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is similar to natural policy gradient methods and is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as input. Despite its approximations that deviate from the theory, TRPO tends to give monotonic improvement, with little tuning of hyperparameters.
This paper has not been read by Pith yet.
Forward citations
Cited by 31 Pith papers
-
High-Dimensional Continuous Control Using Generalized Advantage Estimation
Generalized advantage estimation combined with trust region optimization enables stable neural network policy learning for complex continuous control from raw kinematics.
-
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
-
Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs
Introduces priced face-crossing via normal-fan geometry on occupancy polytopes to decompose dynamic regret into intrinsic motion cost plus within-face error in non-stationary adversarial MDPs.
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
-
What Type of Inference is Active Inference?
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
-
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general functi...
-
Planning in entropy-regularized Markov decision processes and games
SmoothCruiser achieves O~(1/epsilon^4) problem-independent sample complexity for value estimation in entropy-regularized MDPs and games via a generative model.
-
Advantage-Guided Diffusion for Model-Based Reinforcement Learning
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
-
Neural Assistive Impulses: Synthesizing Exaggerated Motions for Physics-based Characters
A hybrid neural policy operating in impulse space enables physics-based characters to track exaggerated, dynamically infeasible motions that standard DRL methods cannot stabilize.
-
An Information-Geometric Approach to Artificial Curiosity
Information geometry constrains intrinsic rewards to strictly concave functions of reciprocal occupancy, with geodesic interpolation on the occupancy manifold yielding a scalar-parameter family that includes count-bas...
-
Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
Temporal Transfer Learning selects source tasks for zero-shot transfer of RL policies to solve a range of coarse-grained advisory autonomy hold durations in traffic optimization more reliably than baselines.
-
Continuous control with deep reinforcement learning
DDPG is a model-free actor-critic algorithm that learns continuous control policies end-to-end from states or pixels using deterministic policy gradients and deep networks, solving more than 20 physics tasks competiti...
-
When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
-
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
Reinforcement learning with semantic rewards lets LLMs gain low-resource language skills without the alignment tax that degrades general capabilities in supervised fine-tuning.
-
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in a unified policy.
-
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.
-
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent ...
-
Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
Shows entropy coupling limits DSAC on discrete tasks and introduces a generalized actor-critic framework with m-step critics and novel entropy-regularized objectives that perform robustly on Atari.
-
Reinforcement Learning-based Control via Y-wise Affine Neural Networks (YANNs)
YANN-RL initializes RL actor and critic networks with explicit multi-parametric linear MPC solutions via YANNs to start from linear optimal control performance and then learn nonlinear policies through online interaction.
-
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
UCOB improves agentic RL by using return-to-go comparisons between skill-conditioned and no-skill prompts as local teachers for bidirectional self-distillation and skill memory updates.
-
Polychromic Objectives for Reinforcement Learning
Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.
-
Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning
A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.
-
$\alpha$-fair heterogeneous agent reinforcement learning
Introduces α-fair HATRPO and HAPPO algorithms that integrate α-fairness into HATRL via a weighted advantage function while claiming to preserve convergence to Nash equilibria.
-
OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
OmniVLA-RL uses a mix-of-transformers architecture and flow-matching reformulated as SDE with group segmented policy optimization to surpass prior VLA models on LIBERO benchmarks.
-
Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback
Themis is an XAI-enabled framework for RL from human feedback that supports 200+ environments and includes a scalable cloud platform for collecting human preferences.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
-
Information-Theoretic Measures in AI: A Practical Decision Guide
A practical guide that organizes seven IT measures around three questions each—what it answers in AI, suitable estimators, and dangerous misuses—complete with flowchart, table, and worked examples.
-
Information-Theoretic Measures in AI: A Practical Decision Guide
A synthesis paper offering a practical decision guide, flowchart, and table for choosing among seven established information-theoretic measures in AI and agent applications.
-
Towards Safe and Robust Autonomous Vehicle Platooning: A Self-Organizing Cooperative Control Framework
TriCoD is a cooperative decision-making framework using twin-world deduction and adaptive switching between DRL and model-driven methods to enable safe, dynamic AV platooning in hybrid traffic.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.
-
Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.