Reinforcement Learning podcasts

Diogo Almeida joins Sam Charrington to discuss TypeSafe's Jev model and the use of calibrated decisions as a component of AI software. The conversation examines reinforcement learning from calibrated decisions, differences from classifiers and text-generating models, and the implications for agents, tool use and system architecture.

Hosted by Sam Charrington

Yuandong Tian discusses his research on computer Go, from DarkForest to OpenGo, and the role of action-space design in applying reinforcement learning. The conversation covers gradient-free optimization, neural architecture search, Coconut’s approach to reasoning in latent space, representation learning and grokking. It then examines AI-assisted research, recursive self-improvement, coding-agent limitations, and whether alternative architectures can outperform transformers. The closing discussion considers data efficiency, robotics, restrictions on self-improving systems, and open-source models.

Hosted by Ravid Shwartz Ziv, Allen Roush

Rohan Anil of Core Automation discusses the relationship between pretraining, reinforcement learning and learning after deployment. Drawing on his optimization work at Google and Anthropic, he examines why additional post-training, distillation and longer contexts may not solve continual learning. Other topics include second-order optimizers, distributed training, low-level coding agents and the difficulty of coordinating very large GPU clusters. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Google DeepMind research director Brendan O'Donoghue examines discrete diffusion as an alternative to autoregressive text generation. He discusses sample diversity, reinforcement learning, latency and potential on-device or robotics applications. The episode also addresses the costs of serving diffusion models, hardware trade-offs between computation and memory bandwidth, and practical limits on progress toward more capable AI. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Fatih Porikli examines why scaling image models alone does not guarantee visually correct results. He discusses separating scene planning from rendering, improving controllability and editing, and bringing high-resolution generation to edge devices, including the role of training objectives and reinforcement learning.

Hosted by Sam Charrington

Nathan Lambert discusses post-training and the prospects for open AI models, drawing on his work on OLMo at Ai2 and his writing on reinforcement learning from human feedback. Topics include capability gaps, the economics of the open ecosystem, training environments, continual learning and skepticism about recursive self-improvement. The conversation also examines research culture, concentrated talent and whether increased model spending translates into better products. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

PufferAI researcher Joseph Suarez argues that implementation and simulation bottlenecks have constrained reinforcement learning as much as algorithm choice. He discusses the design of useful simulators, CPU and GPU trade-offs, faster training pipelines and open-source research tools. The conversation ranges from game environments to potential applications in scientific simulation and biological modelling. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Dhruv Batra connects embodied AI research with browser agents at Yutori. He explains why navigation from pixels to actions links virtual robots and web interaction, then discusses reinforcement learning on live websites, simulation-to-reality gaps and teleoperation. The conversation also examines competing views of intelligence, claims about scaling and the implications of agent-mediated browsing for the web. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Sebastian Raschka reviews changes in language-model research, including reasoning-focused post-training, inference-time computation and reinforcement learning with verifiable rewards. The discussion connects these methods with self-consistency, model architectures, efficient attention and long contexts, while examining limits in continual learning and the reliability of agent workflows.

Hosted by Sam Charrington

Yejin Choi examines how data diversity, synthetic examples, imitation learning and reinforcement learning can strengthen reasoning in small language models. The conversation discusses output homogeneity, Prismatic Synthesis, training models to reason before predicting tokens, and pluralistic alignment that represents a broader range of human values.

Hosted by Sam Charrington

Nikita Rudin discusses reinforcement learning for robot locomotion and the difficulties of transferring policies from simulation to physical robots. Topics include visual inputs, real-world data for improving simulators, imitation learning and teleoperation, hierarchical control, and trade-offs between modular and end-to-end approaches for autonomous robots.

Hosted by Sam Charrington

Devi Parikh discusses browser agents that act through visually grounded models. The conversation examines screenshots as an interface, training with supervised learning, rejection sampling and reinforcement learning, and coordinating tools and sub-agents. It considers reliability and the progression from background monitoring to autonomous web tasks.

Hosted by Sam Charrington

Carina Hong discusses building systems for mathematical reasoning and machine-verifiable proofs. The conversation explores Lean, the scarcity of formal mathematical training data, and translating natural-language arguments into formal statements. It also examines conjecture-and-proof self-play and applications of formal verification to software and hardware.

Hosted by Sam Charrington

Kim Stachenfeld discusses research spanning neuroscience and AI, including reinforcement learning, hippocampal cognitive maps and predictive modelling of physical systems. The conversation considers what each field contributes to the other, how scientific goals differ between academia and industry, and how practical deep-learning work relates to questions about cognition.

Hosted by Paul Middlebrooks